> For the complete documentation index, see [llms.txt](https://docs.aimlapi.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aimlapi.com/api-references/text-models-llm/ml-api/dynamic-router.md).

# Dynamic Router

{% columns %}
{% column width="66.66666666666666%" %}
{% hint style="info" %}
This documentation is valid for the following list of our models:

* `z-ai/glm-5.3-flashx`
  {% endhint %}
  {% endcolumn %}

{% column width="33.33333333333334%" %} <a href="https://aimlapi.com/app/z-ai/glm-5.3-flashx" class="button primary">Try in Playground</a>
{% endcolumn %}
{% endcolumns %}

## Model Overview

A router you configure in the request. Describe up to ten buckets in your own words (`when`), each with the models to try in order, and name the decision model: it picks the bucket whose description fits each chat request, and the first model of that bucket that can take the request answers, falling back to the next one in your order. A bucket with no models (`models: []`) ends the request at the decision: no model is called, the answer is an empty message, and `meta.router` gives your code the bucket to act on (`routed: false`) — only the judgement is charged. One bucket makes a plain fallback chain, with no judgement. Without a `router` object it routes like the Jev Router — light: GPT-6 Luna, DeepSeek V4.1 Flash, Gemini Flash-Lite; standard: GPT-6.1 Sol, Claude Sonnet 5.5; heavy: Claude Opus 5.5, GPT-6 Astra — and a `router` that leaves a setting out keeps its default. You pay the rate of the model that answers, named in `meta.model`, plus the judgement: one decision at its catalogue price, listed as its own request in your usage. `meta.router` says which bucket the request landed in, why, and what the decision model chose and how sure it was.

{% hint style="success" %}
[Create AI/ML API Key](https://aimlapi.com/app/keys)
{% endhint %}

<details>

<summary>How to make the first API call</summary>

**1️⃣ Required setup (don’t skip this)**\
▪ **Create an account:** Sign up on the AI/ML API website (if you don’t have one yet).\
▪ **Generate an API key:** In your account dashboard, create an API key and make sure it’s **enabled** in the UI.

**2️ Copy the code example**\
At the bottom of this page, pick the snippet for your preferred programming language (Python / Node.js) and copy it into your project.

**3️ Update the snippet for your use case**\
▪ **Insert your API key:** replace `<YOUR_AIMLAPI_KEY>` with your real AI/ML API key.\
▪ **Select a model:** set the `model` field to the model you want to call.\
▪ **Provide input:** fill in the request input field(s) shown in the example.

**4️ (Optional) Tune the request**\
See the API schema below for optional generation settings.

**5️ Run your code**\
Run the updated code in your development environment.

{% hint style="success" %}
For a detailed walkthrough, use our [Quickstart guide](https://docs.aimlapi.com/quickstart/setting-up).
{% endhint %}

</details>

## API Schema

## POST /v1/chat/completions

>

```json
{"openapi":"3.0.0","info":{"title":"AIML API","version":"1.0.0"},"servers":[{"url":"https://api.aimlapi.com"}],"paths":{"/v1/chat/completions":{"post":{"operationId":"_v1_chat_completions","requestBody":{"required":true,"content":{"application/json":{"schema":{"anyOf":[{"type":"object","properties":{"model":{"type":"string","enum":["aimlapi/dynamic-router"]},"provider":{"type":"string","description":"Provider routing override. Use a source key such as `openai`, `openrouter`, `xai`, `google`, `alibaba`, `minimax`, `moonshot`, `baidu`, or `togetherai` to run that provider with no fallback; `auto` (default) uses the full fallback chain. Case-insensitive."},"messages":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"role":{"type":"string","enum":["user"],"description":"The role of the author of the message — in this case, the user"},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"type":{"type":"string","enum":["image_url"]},"image_url":{"type":"object","properties":{"url":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"}],"description":"Either a URL of the image or the base64 encoded image data. "},"detail":{"type":"string","enum":["low","high","auto"],"description":"Specifies the detail level of the image. Currently supports JPG/JPEG, PNG, GIF, and WEBP formats."}},"required":["url"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","image_url"]},{"type":"object","properties":{"type":{"type":"string","enum":["file"],"description":"The type of the content part."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]},"file":{"type":"object","properties":{"file_data":{"type":"string","description":"The file data, encoded in base64 and passed to the model as a string. Only PDF format is supported.\n        - Maximum size per file: Up to 512 MB and up to 2 million tokens.\n        - Maximum number of files: Up to 20 files can be attached to a single GPT application or Assistant. This limit applies throughout the application's lifetime.\n        - Maximum total file storage per user: 10 GB."},"file_id":{"type":"string"},"filename":{"type":"string","description":"The file name specified by the user. This name can be used to reference the file when interacting with the model, especially if multiple files are uploaded."}}}},"required":["type","file"]}]}}],"description":"The contents of the user message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the developer message."},"role":{"type":"string","enum":["developer"],"description":"The role of the author of the message — in this case, the developer."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["content","role"]},{"type":"object","properties":{"role":{"type":"string","enum":["system"],"description":"The role of the author of the message — in this case, the system."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the system message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"role":{"type":"string","enum":["tool"],"description":"The role of the author of the message — in this case, the tool."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the tool message."},"tool_call_id":{"type":"string","description":"Tool call that this message is responding to."},"name":{"type":"string","nullable":true,"description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content","tool_call_id"]},{"type":"object","properties":{"role":{"type":"string","enum":["assistant"],"description":"The role of the author of the message — in this case, the Assistant."},"content":{"anyOf":[{"type":"string","description":"The contents of the Assistant message."},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"refusal":{"type":"string","description":"The refusal message generated by the model."},"type":{"type":"string","enum":["refusal"],"description":"The type of the content part."}},"required":["refusal","type"]}]},"description":"An array of content parts with a defined type. Can be one or more of type text, or exactly one of type refusal."},{"nullable":true}],"description":"The contents of the Assistant message. Required unless tool_calls or function_call is specified."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."},"tool_calls":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."},"arguments":{"type":"string","description":"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."}},"required":["name","arguments"],"description":"The function that the model called."},"extra_content":{"type":"object","additionalProperties":{"nullable":true},"description":"Opaque provider metadata for this tool call (e.g. Gemini thought_signature). Echo it back unchanged on the next turn."}},"required":["id","type","function"]},{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool to call."},"input":{"type":"string","description":"The input for the custom tool call generated by the model."}},"required":["name","input"],"description":"The custom tool that the model called."},"extra_content":{"type":"object","additionalProperties":{"nullable":true},"description":"Opaque provider metadata for this tool call (e.g. Gemini thought_signature). Echo it back unchanged on the next turn."}},"required":["id","type","custom"]}]},"description":"The tool calls generated by the model, such as function calls."},"refusal":{"type":"string","nullable":true,"description":"The refusal message by the Assistant."}},"required":["role"]}]},"description":"A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, documents (txt, pdf), images, and audio."},"max_tokens":{"type":"number","minimum":1,"description":"The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API."},"stream":{"type":"boolean","default":false,"description":"If set to True, the model response data will be streamed to the client as it is generated using server-sent events."},"stream_options":{"type":"object","properties":{"include_usage":{"type":"boolean"}},"required":["include_usage"]},"tools":{"type":"array","items":{"anyOf":[{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"description":{"type":"string","description":"A description of what the function does, used by the model to choose when and how to call the function."},"name":{"type":"string","description":"The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."},"parameters":{"type":"object","additionalProperties":{"nullable":true,"description":"The parameters the functions accepts, described as a JSON Schema object."}},"strict":{"type":"boolean","nullable":true,"description":"Whether to enable strict schema adherence when generating the function call. If set to True, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is True."}},"required":["name"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","function"]},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool, used to identify it in tool calls."},"description":{"type":"string","description":"Optional description of the custom tool, used to provide more context."},"format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["grammar"]},"grammar":{"type":"object","properties":{"definition":{"type":"string","description":"The grammar definition."},"syntax":{"type":"string","enum":["lark","regex"],"description":"The syntax of the grammar definition."}},"required":["definition","syntax"]}},"required":["type","grammar"]}],"description":"The input format for the custom tool. Default is unconstrained text."}},"required":["name","format"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","custom"]}]},{"type":"object","properties":{"type":{"type":"string","minLength":1}},"required":["type"]}]},"description":"A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported."},"tool_choice":{"anyOf":[{"type":"string","enum":["none","auto","required"],"description":"none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."}},"required":["name"]}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["allowed_tools"],"description":"The type of the tool. Currently, only function is supported."},"allowed_tools":{"type":"object","properties":{"mode":{"type":"string","enum":["auto","required"],"description":"Constrains the tools available to the model to a pre-defined set.\n- auto allows the model to pick from among the allowed tools and generate a message.\n- required requires the model to call one or more of the allowed tools."},"tools":{"type":"array","items":{"type":"object","additionalProperties":{"nullable":true}},"description":"A list of tool definitions that the model should be allowed to call."}},"required":["mode","tools"]}},"required":["type","allowed_tools"],"description":"Constrains the tools available to the model to a pre-defined set."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"string","enum":["name"],"description":"The name of the function to call."}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"string","enum":["name"],"description":"The name of the custom tool to call."}},"required":["type","custom"],"description":"Specifies a tool the model should use. Use to force the model to call a specific custom tool."}],"description":"Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {\"type\": \"function\", \"function\": {\"name\": \"my_function\"}} forces the model to call that tool.\n  none is the default when no tools are present. auto is the default if tools are present."},"normalize_tool_schemas":{"type":"boolean","description":"Enable provider compatibility normalization for tool function JSON schemas."},"parallel_tool_calls":{"type":"boolean","description":"Whether to enable parallel function calling during tool use."},"n":{"type":"integer","nullable":true,"minimum":1,"description":"How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs."},"seed":{"type":"integer","minimum":1,"description":"This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result."},"reasoning_effort":{"type":"string","enum":["none","low","medium","high"],"description":"Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response."},"response_format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of response format being defined. Always text."}},"required":["type"],"additionalProperties":false,"description":"Default response format. Used to generate text responses."},{"type":"object","properties":{"type":{"type":"string","enum":["json_object"],"description":"The type of response format being defined. Always json_object."}},"required":["type"],"additionalProperties":false,"description":"An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema"],"description":"The type of response format being defined. Always json_schema."},"json_schema":{"type":"object","properties":{"name":{"type":"string","description":"The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."},"schema":{"type":"object","additionalProperties":{"nullable":true},"description":"The schema for the response format, described as a JSON Schema object."},"strict":{"type":"boolean","nullable":true,"description":"Whether to enable strict schema adherence when generating the output. If set to True, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is True."},"description":{"type":"string","description":"A description of what the response format is for, used by the model to determine how to respond in the format."}},"required":["name"],"additionalProperties":false,"description":"JSON Schema response format. Used to generate structured JSON responses."}},"required":["type","json_schema"],"additionalProperties":false,"description":"JSON Schema response format. Used to generate structured JSON responses."}],"description":"An object specifying the format that the model must output."},"router":{"type":"object","properties":{"decision_model":{"type":"string","enum":["typesafe/jev","liquid/d1"],"description":"The decision model that picks each request's bucket. Default `typesafe/jev`. Only decision models are accepted here, never a chat model. Every judgement is billed at that model's catalogue price and listed as its own request in your usage; turns that need none (tool results, a forced bucket, a single bucket) pay nothing for it."},"buckets":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","maxLength":32,"pattern":"^[A-Za-z0-9][A-Za-z0-9_.-]*$","description":"The bucket's name, unique in the router: 1 to 32 letters, digits, `-`, `_` or `.`. Name it in `default_bucket` and `force_bucket`; the response's `meta.router.bucket` says which one answered."},"when":{"type":"string","minLength":1,"maxLength":500,"description":"What the requests this bucket takes look like, in your words (1 to 500 characters) — for example \"unsolicited advertising, prize claims or phishing\". The decision model picks the bucket whose `when` fits each request best. Required on every bucket when there are two or more; a single bucket has none."},"models":{"type":"array","items":{"anyOf":[{"type":"string","description":"A chat model id, as you would pass it in `model` (see `GET /v1/models`)."},{"type":"object","properties":{"model":{"type":"string"}},"required":["model"],"additionalProperties":false,"description":"The same model id, as an object: `{ \"model\": \"<id>\" }`."}],"description":"A chat model this bucket may answer with."},"maxItems":5,"description":"1 to 5 chat models, in the order to try them: the first one that can take the request (its tools, images, JSON schema and context size) answers, and if it fails the next one does. Only chat models we serve — not routers, not decision models. Models you list run with your request's own settings, reasoning included. Or none (`[]`): a request the decision model puts in this bucket ends at the decision — no model is called, and the response is an empty assistant message (`content: \"\"`, `finish_reason: \"stop\"`) whose `meta.router` says `\"routed\": false` and names the bucket, so your code acts on it. Only the judgement is charged. Not on a single bucket, which is never judged."}},"required":["name","models"],"additionalProperties":false,"description":"One bucket: its name, what it takes, and its models."},"minItems":1,"maxItems":10,"description":"Your buckets, 1 to 10: they replace the default buckets entirely. With two or more, each needs a `when`, and the decision model picks the one that fits each request. A single bucket is a fallback chain — every request goes to it, with no judgement. Left out: the default buckets — `light` (\"Needs little capability: greetings and small talk, one-line or lookup answers, common knowledge, short routine tasks such as a short piece of writing, a quick rewrite or simple arithmetic — a small, fast model answers it well\"): `openai/gpt-6-luna`, `deepseek/deepseek-v4.1-flash`, `google/gemini-3-1-flash-lite`, `google/gemini-3-5-flash-lite`; `standard` (\"Needs a capable model: multi-step tasks that need care and accuracy\"): `openai/gpt-6.1-sol`, `anthropic/claude-sonnet-5.5`; `heavy` (\"Needs the strongest model: complex reasoning, hard math or proofs, large or tricky code, expert-level or research-grade knowledge\"): `anthropic/claude-opus-5.5`, `openai/gpt-6-astra`."},"default_bucket":{"type":"string","description":"Where a request goes when it is not judged — the decision model failed, timed out or named no bucket, or the request has no text — and where one goes when none of its bucket's models can take it, before the others are tried. Default: your first bucket; `standard` for the default buckets. Required when your first bucket lists no models: a request that is not judged would otherwise end there, unanswered by any model."},"force_bucket":{"type":"string","description":"Send the request to this bucket without judging it (nothing is charged for a judgement)."},"min_confidence":{"type":"number","minimum":0,"maximum":1,"description":"Below this confidence in its answer (0 to 1), a request goes to `default_bucket` instead (`meta.router.reason`: `unsure`) — for example, send what the decision model is unsure about to your strongest bucket. The judgement is still paid for."}},"additionalProperties":false,"description":"How `aimlapi/dynamic-router` routes this request. Every setting is optional: left out, or `{}`, it routes like `typesafe/jev-router`; a setting you leave out keeps its default, and `buckets`, when given, are the whole table. A conversation stays on its model while its turns land in the same bucket; a turn returning tool results always goes back to the model that made the calls. The response says where the request went in `meta.router` (`routed`, bucket, reason, the decision model's choice and confidence, the judgement and its charge) and which model answered in `meta.model` — the router itself when the bucket lists no models. An invalid configuration is answered with a 400 that names each setting to fix, before anything is charged."}},"required":["model","messages"],"title":"aimlapi/dynamic-router"},{"type":"object","properties":{"model":{"type":"string","enum":["aimlapi/dynamic-router"]},"provider":{"type":"string","description":"Provider routing override. Use a source key such as `openai`, `openrouter`, `xai`, `google`, `alibaba`, `minimax`, `moonshot`, `baidu`, or `togetherai` to run that provider with no fallback; `auto` (default) uses the full fallback chain. Case-insensitive."},"messages":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"role":{"type":"string","enum":["user"],"description":"The role of the author of the message — in this case, the user"},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"type":{"type":"string","enum":["image_url"]},"image_url":{"type":"object","properties":{"url":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"}],"description":"Either a URL of the image or the base64 encoded image data. "},"detail":{"type":"string","enum":["low","high","auto"],"description":"Specifies the detail level of the image. Currently supports JPG/JPEG, PNG, GIF, and WEBP formats."}},"required":["url"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","image_url"]}]}}],"description":"The contents of the user message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"role":{"type":"string","enum":["system"],"description":"The role of the author of the message — in this case, the system."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the system message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"role":{"type":"string","enum":["tool"],"description":"The role of the author of the message — in this case, the tool."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the tool message."},"tool_call_id":{"type":"string","description":"Tool call that this message is responding to."},"name":{"type":"string","nullable":true,"description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content","tool_call_id"]},{"type":"object","properties":{"role":{"type":"string","enum":["assistant"],"description":"The role of the author of the message — in this case, the Assistant."},"content":{"anyOf":[{"type":"string","description":"The contents of the Assistant message."},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"refusal":{"type":"string","description":"The refusal message generated by the model."},"type":{"type":"string","enum":["refusal"],"description":"The type of the content part."}},"required":["refusal","type"]}]},"description":"An array of content parts with a defined type. Can be one or more of type text, or exactly one of type refusal."},{"nullable":true}],"description":"The contents of the Assistant message. Required unless tool_calls or function_call is specified."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."},"tool_calls":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."},"arguments":{"type":"string","description":"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."}},"required":["name","arguments"],"description":"The function that the model called."},"extra_content":{"type":"object","additionalProperties":{"nullable":true},"description":"Opaque provider metadata for this tool call (e.g. Gemini thought_signature). Echo it back unchanged on the next turn."}},"required":["id","type","function"]},{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool to call."},"input":{"type":"string","description":"The input for the custom tool call generated by the model."}},"required":["name","input"],"description":"The custom tool that the model called."},"extra_content":{"type":"object","additionalProperties":{"nullable":true},"description":"Opaque provider metadata for this tool call (e.g. Gemini thought_signature). Echo it back unchanged on the next turn."}},"required":["id","type","custom"]}]},"description":"The tool calls generated by the model, such as function calls."},"refusal":{"type":"string","nullable":true,"description":"The refusal message by the Assistant."}},"required":["role"]}]},"description":"A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, documents (txt, pdf), images, and audio."},"max_completion_tokens":{"type":"integer","minimum":1,"description":"An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens."},"max_tokens":{"type":"number","minimum":1,"description":"The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API."},"stream":{"type":"boolean","default":false,"description":"If set to True, the model response data will be streamed to the client as it is generated using server-sent events."},"stream_options":{"type":"object","properties":{"include_usage":{"type":"boolean"}},"required":["include_usage"]},"tools":{"type":"array","items":{"anyOf":[{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"description":{"type":"string","description":"A description of what the function does, used by the model to choose when and how to call the function."},"name":{"type":"string","description":"The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."},"parameters":{"type":"object","additionalProperties":{"nullable":true,"description":"The parameters the functions accepts, described as a JSON Schema object."}},"strict":{"type":"boolean","nullable":true,"description":"Whether to enable strict schema adherence when generating the function call. If set to True, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is True."}},"required":["name"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","function"]},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool, used to identify it in tool calls."},"description":{"type":"string","description":"Optional description of the custom tool, used to provide more context."},"format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["grammar"]},"grammar":{"type":"object","properties":{"definition":{"type":"string","description":"The grammar definition."},"syntax":{"type":"string","enum":["lark","regex"],"description":"The syntax of the grammar definition."}},"required":["definition","syntax"]}},"required":["type","grammar"]}],"description":"The input format for the custom tool. Default is unconstrained text."}},"required":["name","format"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","custom"]}]},{"type":"object","properties":{"type":{"type":"string","minLength":1}},"required":["type"]}]},"description":"A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported."},"tool_choice":{"anyOf":[{"type":"string","enum":["none","auto","required"],"description":"none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."}},"required":["name"]}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["allowed_tools"],"description":"The type of the tool. Currently, only function is supported."},"allowed_tools":{"type":"object","properties":{"mode":{"type":"string","enum":["auto","required"],"description":"Constrains the tools available to the model to a pre-defined set.\n- auto allows the model to pick from among the allowed tools and generate a message.\n- required requires the model to call one or more of the allowed tools."},"tools":{"type":"array","items":{"type":"object","additionalProperties":{"nullable":true}},"description":"A list of tool definitions that the model should be allowed to call."}},"required":["mode","tools"]}},"required":["type","allowed_tools"],"description":"Constrains the tools available to the model to a pre-defined set."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"string","enum":["name"],"description":"The name of the function to call."}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"string","enum":["name"],"description":"The name of the custom tool to call."}},"required":["type","custom"],"description":"Specifies a tool the model should use. Use to force the model to call a specific custom tool."}],"description":"Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {\"type\": \"function\", \"function\": {\"name\": \"my_function\"}} forces the model to call that tool.\n  none is the default when no tools are present. auto is the default if tools are present."},"normalize_tool_schemas":{"type":"boolean","description":"Enable provider compatibility normalization for tool function JSON schemas."},"temperature":{"type":"number","minimum":0,"maximum":2,"description":"What sampling temperature to use. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both."},"top_p":{"type":"number","minimum":0.01,"maximum":1,"description":"An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n  We generally recommend altering this or temperature but not both."},"stop":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}},{"nullable":true}],"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."},"logprobs":{"type":"boolean","nullable":true,"description":"Whether to return log probabilities of the output tokens or not. If True, returns the log probabilities of each output token returned in the content of message."},"top_logprobs":{"type":"number","nullable":true,"minimum":0,"maximum":20,"description":"An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to True if this parameter is used."},"frequency_penalty":{"type":"number","nullable":true,"minimum":-2,"maximum":2,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","nullable":true,"minimum":-2,"maximum":2,"description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"reasoning_effort":{"type":"string","enum":["none","low","medium","high"],"description":"Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response."},"reasoning":{"type":"object","properties":{"effort":{"type":"string","enum":["low","medium","high"],"description":"Reasoning effort setting"},"max_tokens":{"type":"integer","minimum":1,"description":"Max tokens of reasoning content. Cannot be used simultaneously with effort."},"exclude":{"type":"boolean","description":"Whether to exclude reasoning from the response"}},"description":"Configuration for model reasoning/thinking tokens"},"response_format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of response format being defined. Always text."}},"required":["type"],"additionalProperties":false,"description":"Default response format. Used to generate text responses."},{"type":"object","properties":{"type":{"type":"string","enum":["json_object"],"description":"The type of response format being defined. Always json_object."}},"required":["type"],"additionalProperties":false,"description":"An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so."}],"description":"An object specifying the format that the model must output."},"router":{"type":"object","properties":{"decision_model":{"type":"string","enum":["typesafe/jev","liquid/d1"],"description":"The decision model that picks each request's bucket. Default `typesafe/jev`. Only decision models are accepted here, never a chat model. Every judgement is billed at that model's catalogue price and listed as its own request in your usage; turns that need none (tool results, a forced bucket, a single bucket) pay nothing for it."},"buckets":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","maxLength":32,"pattern":"^[A-Za-z0-9][A-Za-z0-9_.-]*$","description":"The bucket's name, unique in the router: 1 to 32 letters, digits, `-`, `_` or `.`. Name it in `default_bucket` and `force_bucket`; the response's `meta.router.bucket` says which one answered."},"when":{"type":"string","minLength":1,"maxLength":500,"description":"What the requests this bucket takes look like, in your words (1 to 500 characters) — for example \"unsolicited advertising, prize claims or phishing\". The decision model picks the bucket whose `when` fits each request best. Required on every bucket when there are two or more; a single bucket has none."},"models":{"type":"array","items":{"anyOf":[{"type":"string","description":"A chat model id, as you would pass it in `model` (see `GET /v1/models`)."},{"type":"object","properties":{"model":{"type":"string"}},"required":["model"],"additionalProperties":false,"description":"The same model id, as an object: `{ \"model\": \"<id>\" }`."}],"description":"A chat model this bucket may answer with."},"maxItems":5,"description":"1 to 5 chat models, in the order to try them: the first one that can take the request (its tools, images, JSON schema and context size) answers, and if it fails the next one does. Only chat models we serve — not routers, not decision models. Models you list run with your request's own settings, reasoning included. Or none (`[]`): a request the decision model puts in this bucket ends at the decision — no model is called, and the response is an empty assistant message (`content: \"\"`, `finish_reason: \"stop\"`) whose `meta.router` says `\"routed\": false` and names the bucket, so your code acts on it. Only the judgement is charged. Not on a single bucket, which is never judged."}},"required":["name","models"],"additionalProperties":false,"description":"One bucket: its name, what it takes, and its models."},"minItems":1,"maxItems":10,"description":"Your buckets, 1 to 10: they replace the default buckets entirely. With two or more, each needs a `when`, and the decision model picks the one that fits each request. A single bucket is a fallback chain — every request goes to it, with no judgement. Left out: the default buckets — `light` (\"Needs little capability: greetings and small talk, one-line or lookup answers, common knowledge, short routine tasks such as a short piece of writing, a quick rewrite or simple arithmetic — a small, fast model answers it well\"): `openai/gpt-6-luna`, `deepseek/deepseek-v4.1-flash`, `google/gemini-3-1-flash-lite`, `google/gemini-3-5-flash-lite`; `standard` (\"Needs a capable model: multi-step tasks that need care and accuracy\"): `openai/gpt-6.1-sol`, `anthropic/claude-sonnet-5.5`; `heavy` (\"Needs the strongest model: complex reasoning, hard math or proofs, large or tricky code, expert-level or research-grade knowledge\"): `anthropic/claude-opus-5.5`, `openai/gpt-6-astra`."},"default_bucket":{"type":"string","description":"Where a request goes when it is not judged — the decision model failed, timed out or named no bucket, or the request has no text — and where one goes when none of its bucket's models can take it, before the others are tried. Default: your first bucket; `standard` for the default buckets. Required when your first bucket lists no models: a request that is not judged would otherwise end there, unanswered by any model."},"force_bucket":{"type":"string","description":"Send the request to this bucket without judging it (nothing is charged for a judgement)."},"min_confidence":{"type":"number","minimum":0,"maximum":1,"description":"Below this confidence in its answer (0 to 1), a request goes to `default_bucket` instead (`meta.router.reason`: `unsure`) — for example, send what the decision model is unsure about to your strongest bucket. The judgement is still paid for."}},"additionalProperties":false,"description":"How `aimlapi/dynamic-router` routes this request. Every setting is optional: left out, or `{}`, it routes like `typesafe/jev-router`; a setting you leave out keeps its default, and `buckets`, when given, are the whole table. A conversation stays on its model while its turns land in the same bucket; a turn returning tool results always goes back to the model that made the calls. The response says where the request went in `meta.router` (`routed`, bucket, reason, the decision model's choice and confidence, the judgement and its charge) and which model answered in `meta.model` — the router itself when the bucket lists no models. An invalid configuration is answered with a 400 that names each setting to fix, before anything is charged."}},"required":["model","messages"],"title":"aimlapi/dynamic-router"},{"type":"object","properties":{"model":{"type":"string","enum":["aimlapi/dynamic-router"]},"provider":{"type":"string","description":"Provider routing override. Use a source key such as `openai`, `openrouter`, `xai`, `google`, `alibaba`, `minimax`, `moonshot`, `baidu`, or `togetherai` to run that provider with no fallback; `auto` (default) uses the full fallback chain. Case-insensitive."},"messages":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"role":{"type":"string","enum":["user"],"description":"The role of the author of the message — in this case, the user"},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"type":{"type":"string","enum":["image_url"]},"image_url":{"type":"object","properties":{"url":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"}],"description":"Either a URL of the image or the base64 encoded image data. "},"detail":{"type":"string","enum":["low","high","auto"],"description":"Specifies the detail level of the image. Currently supports JPG/JPEG, PNG, GIF, and WEBP formats."}},"required":["url"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","image_url"]},{"type":"object","properties":{"type":{"type":"string","enum":["video_url"]},"video_url":{"type":"object","properties":{"url":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"}],"description":"Base64-encoded local video file."}},"required":["url"]}},"required":["type","video_url"]},{"type":"object","properties":{"type":{"type":"string","enum":["file"],"description":"The type of the content part."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]},"file":{"type":"object","properties":{"file_data":{"type":"string","description":"The file data, encoded in base64 and passed to the model as a string. Only PDF format is supported.\n        - Maximum size per file: Up to 512 MB and up to 2 million tokens.\n        - Maximum number of files: Up to 20 files can be attached to a single GPT application or Assistant. This limit applies throughout the application's lifetime.\n        - Maximum total file storage per user: 10 GB."},"file_id":{"type":"string"},"filename":{"type":"string","description":"The file name specified by the user. This name can be used to reference the file when interacting with the model, especially if multiple files are uploaded."}}}},"required":["type","file"]},{"type":"object","properties":{"type":{"type":"string","enum":["input_audio"],"description":"The type of the content part."},"input_audio":{"type":"object","properties":{"data":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"},{"type":"string"}],"description":"Either a URL of the audio or the base64 encoded audio data."},"format":{"type":"string","enum":["wav","mp3","audio/x-aac","audio/flac","audio/mp3","audio/m4a","audio/mpeg","audio/mpga","audio/mp4","audio/ogg","audio/pcm","audio/webm"],"description":"The format of the encoded audio data. Currently supports \"wav\" and \"mp3\"."}},"required":["data","format"]}},"required":["type","input_audio"]}]}}],"description":"The contents of the user message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"role":{"type":"string","enum":["system"],"description":"The role of the author of the message — in this case, the system."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the system message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"role":{"type":"string","enum":["tool"],"description":"The role of the author of the message — in this case, the tool."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the tool message."},"tool_call_id":{"type":"string","description":"Tool call that this message is responding to."},"name":{"type":"string","nullable":true,"description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content","tool_call_id"]},{"type":"object","properties":{"role":{"type":"string","enum":["assistant"],"description":"The role of the author of the message — in this case, the Assistant."},"content":{"anyOf":[{"type":"string","description":"The contents of the Assistant message."},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"refusal":{"type":"string","description":"The refusal message generated by the model."},"type":{"type":"string","enum":["refusal"],"description":"The type of the content part."}},"required":["refusal","type"]}]},"description":"An array of content parts with a defined type. Can be one or more of type text, or exactly one of type refusal."},{"nullable":true}],"description":"The contents of the Assistant message. Required unless tool_calls or function_call is specified."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."},"tool_calls":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."},"arguments":{"type":"string","description":"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."}},"required":["name","arguments"],"description":"The function that the model called."},"extra_content":{"type":"object","additionalProperties":{"nullable":true},"description":"Opaque provider metadata for this tool call (e.g. Gemini thought_signature). Echo it back unchanged on the next turn."}},"required":["id","type","function"]},{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool to call."},"input":{"type":"string","description":"The input for the custom tool call generated by the model."}},"required":["name","input"],"description":"The custom tool that the model called."},"extra_content":{"type":"object","additionalProperties":{"nullable":true},"description":"Opaque provider metadata for this tool call (e.g. Gemini thought_signature). Echo it back unchanged on the next turn."}},"required":["id","type","custom"]}]},"description":"The tool calls generated by the model, such as function calls."},"refusal":{"type":"string","nullable":true,"description":"The refusal message by the Assistant."},"audio":{"type":"object","nullable":true,"properties":{"id":{"type":"string","description":"Unique identifier for a previous audio response from the model."}},"required":["id"],"description":"Data about a previous audio response from the model."}},"required":["role"]}]},"description":"A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, documents (txt, pdf), images, and audio."},"max_completion_tokens":{"type":"integer","minimum":1,"description":"An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens."},"max_tokens":{"type":"number","minimum":1,"description":"The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API."},"stream":{"type":"boolean","default":false,"description":"If set to True, the model response data will be streamed to the client as it is generated using server-sent events."},"stream_options":{"type":"object","properties":{"include_usage":{"type":"boolean"}},"required":["include_usage"]},"audio":{"type":"object","nullable":true,"properties":{"format":{"type":"string","enum":["wav","mp3","flac","opus","pcm16"],"description":"Specifies the output audio format. Must be one of wav, mp3, flac, opus, or pcm16."},"voice":{"anyOf":[{"type":"string","enum":["alloy","ash","ballad","coral","echo","fable","nova","onyx","sage","shimmer"]},{"type":"string"}],"description":"The voice the model uses to respond. Supported voices are alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, and shimmer."}},"required":["format","voice"],"description":"Parameters for audio output. Required when audio output is requested with modalities: [\"audio\"]."},"modalities":{"type":"array","nullable":true,"items":{"type":"string","enum":["text","audio"]},"description":"Output types that you would like the model to generate. Most models are capable of generating text, which is the default:\n  \n  [\"text\"]\n  \n  Model can also be used to generate audio. To request that this model generate both text and audio responses, you can use:\n  \n  [\"text\", \"audio\"]"},"n":{"type":"integer","nullable":true,"minimum":1,"description":"How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs."},"temperature":{"type":"number","minimum":0,"maximum":2,"description":"What sampling temperature to use. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both."},"top_p":{"type":"number","minimum":0.01,"maximum":1,"description":"An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n  We generally recommend altering this or temperature but not both."},"stop":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}},{"nullable":true}],"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."},"frequency_penalty":{"type":"number","nullable":true,"minimum":-2,"maximum":2,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim."},"prediction":{"type":"object","properties":{"type":{"type":"string","enum":["content"],"description":"The type of the predicted content you want to provide."},"content":{"anyOf":[{"type":"string","description":"The content used for a Predicted Output. This is often the text of a file you are regenerating with minor changes."},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."}},"required":["type","text"]},"description":"An array of content parts with a defined type. Supported options differ based on the model being used to generate the response. Can contain text inputs."}],"description":"The content that should be matched when generating a model response. If generated tokens would match this content, the entire model response can be returned much more quickly."}},"required":["type","content"],"description":"Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time."},"presence_penalty":{"type":"number","nullable":true,"minimum":-2,"maximum":2,"description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"seed":{"type":"integer","minimum":1,"description":"This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result."},"response_format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of response format being defined. Always text."}},"required":["type"],"additionalProperties":false,"description":"Default response format. Used to generate text responses."},{"type":"object","properties":{"type":{"type":"string","enum":["json_object"],"description":"The type of response format being defined. Always json_object."}},"required":["type"],"additionalProperties":false,"description":"An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema"],"description":"The type of response format being defined. Always json_schema."},"json_schema":{"type":"object","properties":{"name":{"type":"string","description":"The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."},"schema":{"type":"object","additionalProperties":{"nullable":true},"description":"The schema for the response format, described as a JSON Schema object."},"strict":{"type":"boolean","nullable":true,"description":"Whether to enable strict schema adherence when generating the output. If set to True, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is True."},"description":{"type":"string","description":"A description of what the response format is for, used by the model to determine how to respond in the format."}},"required":["name"],"additionalProperties":false,"description":"JSON Schema response format. Used to generate structured JSON responses."}},"required":["type","json_schema"],"additionalProperties":false,"description":"JSON Schema response format. Used to generate structured JSON responses."}],"description":"An object specifying the format that the model must output."},"tools":{"type":"array","items":{"anyOf":[{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"description":{"type":"string","description":"A description of what the function does, used by the model to choose when and how to call the function."},"name":{"type":"string","description":"The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."},"parameters":{"type":"object","additionalProperties":{"nullable":true,"description":"The parameters the functions accepts, described as a JSON Schema object."}},"strict":{"type":"boolean","nullable":true,"description":"Whether to enable strict schema adherence when generating the function call. If set to True, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is True."}},"required":["name"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","function"]},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool, used to identify it in tool calls."},"description":{"type":"string","description":"Optional description of the custom tool, used to provide more context."},"format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["grammar"]},"grammar":{"type":"object","properties":{"definition":{"type":"string","description":"The grammar definition."},"syntax":{"type":"string","enum":["lark","regex"],"description":"The syntax of the grammar definition."}},"required":["definition","syntax"]}},"required":["type","grammar"]}],"description":"The input format for the custom tool. Default is unconstrained text."}},"required":["name","format"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","custom"]}]},{"type":"object","properties":{"type":{"type":"string","minLength":1}},"required":["type"]}]},"description":"A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported."},"tool_choice":{"anyOf":[{"type":"string","enum":["none","auto","required"],"description":"none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."}},"required":["name"]}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["allowed_tools"],"description":"The type of the tool. Currently, only function is supported."},"allowed_tools":{"type":"object","properties":{"mode":{"type":"string","enum":["auto","required"],"description":"Constrains the tools available to the model to a pre-defined set.\n- auto allows the model to pick from among the allowed tools and generate a message.\n- required requires the model to call one or more of the allowed tools."},"tools":{"type":"array","items":{"type":"object","additionalProperties":{"nullable":true}},"description":"A list of tool definitions that the model should be allowed to call."}},"required":["mode","tools"]}},"required":["type","allowed_tools"],"description":"Constrains the tools available to the model to a pre-defined set."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"string","enum":["name"],"description":"The name of the function to call."}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"string","enum":["name"],"description":"The name of the custom tool to call."}},"required":["type","custom"],"description":"Specifies a tool the model should use. Use to force the model to call a specific custom tool."}],"description":"Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {\"type\": \"function\", \"function\": {\"name\": \"my_function\"}} forces the model to call that tool.\n  none is the default when no tools are present. auto is the default if tools are present."},"normalize_tool_schemas":{"type":"boolean","description":"Enable provider compatibility normalization for tool function JSON schemas."},"parallel_tool_calls":{"type":"boolean","description":"Whether to enable parallel function calling during tool use."},"reasoning_effort":{"type":"string","enum":["minimal","low","medium","high","max"],"description":"Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response."},"router":{"type":"object","properties":{"decision_model":{"type":"string","enum":["typesafe/jev","liquid/d1"],"description":"The decision model that picks each request's bucket. Default `typesafe/jev`. Only decision models are accepted here, never a chat model. Every judgement is billed at that model's catalogue price and listed as its own request in your usage; turns that need none (tool results, a forced bucket, a single bucket) pay nothing for it."},"buckets":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","maxLength":32,"pattern":"^[A-Za-z0-9][A-Za-z0-9_.-]*$","description":"The bucket's name, unique in the router: 1 to 32 letters, digits, `-`, `_` or `.`. Name it in `default_bucket` and `force_bucket`; the response's `meta.router.bucket` says which one answered."},"when":{"type":"string","minLength":1,"maxLength":500,"description":"What the requests this bucket takes look like, in your words (1 to 500 characters) — for example \"unsolicited advertising, prize claims or phishing\". The decision model picks the bucket whose `when` fits each request best. Required on every bucket when there are two or more; a single bucket has none."},"models":{"type":"array","items":{"anyOf":[{"type":"string","description":"A chat model id, as you would pass it in `model` (see `GET /v1/models`)."},{"type":"object","properties":{"model":{"type":"string"}},"required":["model"],"additionalProperties":false,"description":"The same model id, as an object: `{ \"model\": \"<id>\" }`."}],"description":"A chat model this bucket may answer with."},"maxItems":5,"description":"1 to 5 chat models, in the order to try them: the first one that can take the request (its tools, images, JSON schema and context size) answers, and if it fails the next one does. Only chat models we serve — not routers, not decision models. Models you list run with your request's own settings, reasoning included. Or none (`[]`): a request the decision model puts in this bucket ends at the decision — no model is called, and the response is an empty assistant message (`content: \"\"`, `finish_reason: \"stop\"`) whose `meta.router` says `\"routed\": false` and names the bucket, so your code acts on it. Only the judgement is charged. Not on a single bucket, which is never judged."}},"required":["name","models"],"additionalProperties":false,"description":"One bucket: its name, what it takes, and its models."},"minItems":1,"maxItems":10,"description":"Your buckets, 1 to 10: they replace the default buckets entirely. With two or more, each needs a `when`, and the decision model picks the one that fits each request. A single bucket is a fallback chain — every request goes to it, with no judgement. Left out: the default buckets — `light` (\"Needs little capability: greetings and small talk, one-line or lookup answers, common knowledge, short routine tasks such as a short piece of writing, a quick rewrite or simple arithmetic — a small, fast model answers it well\"): `openai/gpt-6-luna`, `deepseek/deepseek-v4.1-flash`, `google/gemini-3-1-flash-lite`, `google/gemini-3-5-flash-lite`; `standard` (\"Needs a capable model: multi-step tasks that need care and accuracy\"): `openai/gpt-6.1-sol`, `anthropic/claude-sonnet-5.5`; `heavy` (\"Needs the strongest model: complex reasoning, hard math or proofs, large or tricky code, expert-level or research-grade knowledge\"): `anthropic/claude-opus-5.5`, `openai/gpt-6-astra`."},"default_bucket":{"type":"string","description":"Where a request goes when it is not judged — the decision model failed, timed out or named no bucket, or the request has no text — and where one goes when none of its bucket's models can take it, before the others are tried. Default: your first bucket; `standard` for the default buckets. Required when your first bucket lists no models: a request that is not judged would otherwise end there, unanswered by any model."},"force_bucket":{"type":"string","description":"Send the request to this bucket without judging it (nothing is charged for a judgement)."},"min_confidence":{"type":"number","minimum":0,"maximum":1,"description":"Below this confidence in its answer (0 to 1), a request goes to `default_bucket` instead (`meta.router.reason`: `unsure`) — for example, send what the decision model is unsure about to your strongest bucket. The judgement is still paid for."}},"additionalProperties":false,"description":"How `aimlapi/dynamic-router` routes this request. Every setting is optional: left out, or `{}`, it routes like `typesafe/jev-router`; a setting you leave out keeps its default, and `buckets`, when given, are the whole table. A conversation stays on its model while its turns land in the same bucket; a turn returning tool results always goes back to the model that made the calls. The response says where the request went in `meta.router` (`routed`, bucket, reason, the decision model's choice and confidence, the judgement and its charge) and which model answered in `meta.model` — the router itself when the bucket lists no models. An invalid configuration is answered with a 400 that names each setting to fix, before anything is charged."}},"required":["model","messages"],"title":"aimlapi/dynamic-router"},{"type":"object","properties":{"model":{"type":"string","enum":["aimlapi/dynamic-router"]},"provider":{"type":"string","description":"Provider routing override. Use a source key such as `openai`, `openrouter`, `xai`, `google`, `alibaba`, `minimax`, `moonshot`, `baidu`, or `togetherai` to run that provider with no fallback; `auto` (default) uses the full fallback chain. Case-insensitive."},"messages":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"role":{"type":"string","enum":["user"],"description":"The role of the author of the message — in this case, the user"},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"type":{"type":"string","enum":["image_url"]},"image_url":{"type":"object","properties":{"url":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"}],"description":"Either a URL of the image or the base64 encoded image data. "},"detail":{"type":"string","enum":["low","high","auto"],"description":"Specifies the detail level of the image. Currently supports JPG/JPEG, PNG, GIF, and WEBP formats."}},"required":["url"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","image_url"]},{"type":"object","properties":{"type":{"type":"string","enum":["video_url"]},"video_url":{"type":"object","properties":{"url":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"}],"description":"Base64-encoded local video file."}},"required":["url"]}},"required":["type","video_url"]},{"type":"object","properties":{"type":{"type":"string","enum":["file"],"description":"The type of the content part."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]},"file":{"type":"object","properties":{"file_data":{"type":"string","description":"The file data, encoded in base64 and passed to the model as a string. Only PDF format is supported.\n        - Maximum size per file: Up to 512 MB and up to 2 million tokens.\n        - Maximum number of files: Up to 20 files can be attached to a single GPT application or Assistant. This limit applies throughout the application's lifetime.\n        - Maximum total file storage per user: 10 GB."},"file_id":{"type":"string"},"filename":{"type":"string","description":"The file name specified by the user. This name can be used to reference the file when interacting with the model, especially if multiple files are uploaded."}}}},"required":["type","file"]},{"type":"object","properties":{"type":{"type":"string","enum":["input_audio"],"description":"The type of the content part."},"input_audio":{"type":"object","properties":{"data":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"},{"type":"string"}],"description":"Either a URL of the audio or the base64 encoded audio data."},"format":{"type":"string","enum":["wav","mp3","audio/x-aac","audio/flac","audio/mp3","audio/m4a","audio/mpeg","audio/mpga","audio/mp4","audio/ogg","audio/pcm","audio/webm"],"description":"The format of the encoded audio data. Currently supports \"wav\" and \"mp3\"."}},"required":["data","format"]}},"required":["type","input_audio"]}]}}],"description":"The contents of the user message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"role":{"type":"string","enum":["system"],"description":"The role of the author of the message — in this case, the system."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the system message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"role":{"type":"string","enum":["tool"],"description":"The role of the author of the message — in this case, the tool."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the tool message."},"tool_call_id":{"type":"string","description":"Tool call that this message is responding to."},"name":{"type":"string","nullable":true,"description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content","tool_call_id"]},{"type":"object","properties":{"role":{"type":"string","enum":["assistant"],"description":"The role of the author of the message — in this case, the Assistant."},"content":{"anyOf":[{"type":"string","description":"The contents of the Assistant message."},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"refusal":{"type":"string","description":"The refusal message generated by the model."},"type":{"type":"string","enum":["refusal"],"description":"The type of the content part."}},"required":["refusal","type"]}]},"description":"An array of content parts with a defined type. Can be one or more of type text, or exactly one of type refusal."},{"nullable":true}],"description":"The contents of the Assistant message. Required unless tool_calls or function_call is specified."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."},"tool_calls":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."},"arguments":{"type":"string","description":"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."}},"required":["name","arguments"],"description":"The function that the model called."},"extra_content":{"type":"object","additionalProperties":{"nullable":true},"description":"Opaque provider metadata for this tool call (e.g. Gemini thought_signature). Echo it back unchanged on the next turn."}},"required":["id","type","function"]},{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool to call."},"input":{"type":"string","description":"The input for the custom tool call generated by the model."}},"required":["name","input"],"description":"The custom tool that the model called."},"extra_content":{"type":"object","additionalProperties":{"nullable":true},"description":"Opaque provider metadata for this tool call (e.g. Gemini thought_signature). Echo it back unchanged on the next turn."}},"required":["id","type","custom"]}]},"description":"The tool calls generated by the model, such as function calls."},"refusal":{"type":"string","nullable":true,"description":"The refusal message by the Assistant."},"audio":{"type":"object","nullable":true,"properties":{"id":{"type":"string","description":"Unique identifier for a previous audio response from the model."}},"required":["id"],"description":"Data about a previous audio response from the model."}},"required":["role"]}]},"description":"A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, documents (txt, pdf), images, and audio."},"max_completion_tokens":{"type":"integer","minimum":1,"description":"An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens."},"max_tokens":{"type":"number","minimum":1,"description":"The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API."},"stream":{"type":"boolean","default":false,"description":"If set to True, the model response data will be streamed to the client as it is generated using server-sent events."},"stream_options":{"type":"object","properties":{"include_usage":{"type":"boolean"}},"required":["include_usage"]},"audio":{"type":"object","nullable":true,"properties":{"format":{"type":"string","enum":["wav","mp3","flac","opus","pcm16"],"description":"Specifies the output audio format. Must be one of wav, mp3, flac, opus, or pcm16."},"voice":{"anyOf":[{"type":"string","enum":["alloy","ash","ballad","coral","echo","fable","nova","onyx","sage","shimmer"]},{"type":"string"}],"description":"The voice the model uses to respond. Supported voices are alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, and shimmer."}},"required":["format","voice"],"description":"Parameters for audio output. Required when audio output is requested with modalities: [\"audio\"]."},"modalities":{"type":"array","nullable":true,"items":{"type":"string","enum":["text","audio"]},"description":"Output types that you would like the model to generate. Most models are capable of generating text, which is the default:\n  \n  [\"text\"]\n  \n  Model can also be used to generate audio. To request that this model generate both text and audio responses, you can use:\n  \n  [\"text\", \"audio\"]"},"n":{"type":"integer","nullable":true,"minimum":1,"description":"How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs."},"temperature":{"type":"number","minimum":0,"maximum":2,"description":"What sampling temperature to use. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both."},"top_p":{"type":"number","minimum":0.01,"maximum":1,"description":"An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n  We generally recommend altering this or temperature but not both."},"stop":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}},{"nullable":true}],"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."},"prediction":{"type":"object","properties":{"type":{"type":"string","enum":["content"],"description":"The type of the predicted content you want to provide."},"content":{"anyOf":[{"type":"string","description":"The content used for a Predicted Output. This is often the text of a file you are regenerating with minor changes."},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."}},"required":["type","text"]},"description":"An array of content parts with a defined type. Supported options differ based on the model being used to generate the response. Can contain text inputs."}],"description":"The content that should be matched when generating a model response. If generated tokens would match this content, the entire model response can be returned much more quickly."}},"required":["type","content"],"description":"Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time."},"seed":{"type":"integer","minimum":1,"description":"This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result."},"response_format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of response format being defined. Always text."}},"required":["type"],"additionalProperties":false,"description":"Default response format. Used to generate text responses."},{"type":"object","properties":{"type":{"type":"string","enum":["json_object"],"description":"The type of response format being defined. Always json_object."}},"required":["type"],"additionalProperties":false,"description":"An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema"],"description":"The type of response format being defined. Always json_schema."},"json_schema":{"type":"object","properties":{"name":{"type":"string","description":"The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."},"schema":{"type":"object","additionalProperties":{"nullable":true},"description":"The schema for the response format, described as a JSON Schema object."},"strict":{"type":"boolean","nullable":true,"description":"Whether to enable strict schema adherence when generating the output. If set to True, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is True."},"description":{"type":"string","description":"A description of what the response format is for, used by the model to determine how to respond in the format."}},"required":["name"],"additionalProperties":false,"description":"JSON Schema response format. Used to generate structured JSON responses."}},"required":["type","json_schema"],"additionalProperties":false,"description":"JSON Schema response format. Used to generate structured JSON responses."}],"description":"An object specifying the format that the model must output."},"tools":{"type":"array","items":{"anyOf":[{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"description":{"type":"string","description":"A description of what the function does, used by the model to choose when and how to call the function."},"name":{"type":"string","description":"The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."},"parameters":{"type":"object","additionalProperties":{"nullable":true,"description":"The parameters the functions accepts, described as a JSON Schema object."}},"strict":{"type":"boolean","nullable":true,"description":"Whether to enable strict schema adherence when generating the function call. If set to True, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is True."}},"required":["name"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","function"]},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool, used to identify it in tool calls."},"description":{"type":"string","description":"Optional description of the custom tool, used to provide more context."},"format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["grammar"]},"grammar":{"type":"object","properties":{"definition":{"type":"string","description":"The grammar definition."},"syntax":{"type":"string","enum":["lark","regex"],"description":"The syntax of the grammar definition."}},"required":["definition","syntax"]}},"required":["type","grammar"]}],"description":"The input format for the custom tool. Default is unconstrained text."}},"required":["name","format"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","custom"]}]},{"type":"object","properties":{"type":{"type":"string","minLength":1}},"required":["type"]}]},"description":"A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported."},"tool_choice":{"anyOf":[{"type":"string","enum":["none","auto","required"],"description":"none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."}},"required":["name"]}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["allowed_tools"],"description":"The type of the tool. Currently, only function is supported."},"allowed_tools":{"type":"object","properties":{"mode":{"type":"string","enum":["auto","required"],"description":"Constrains the tools available to the model to a pre-defined set.\n- auto allows the model to pick from among the allowed tools and generate a message.\n- required requires the model to call one or more of the allowed tools."},"tools":{"type":"array","items":{"type":"object","additionalProperties":{"nullable":true}},"description":"A list of tool definitions that the model should be allowed to call."}},"required":["mode","tools"]}},"required":["type","allowed_tools"],"description":"Constrains the tools available to the model to a pre-defined set."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"string","enum":["name"],"description":"The name of the function to call."}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"string","enum":["name"],"description":"The name of the custom tool to call."}},"required":["type","custom"],"description":"Specifies a tool the model should use. Use to force the model to call a specific custom tool."}],"description":"Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {\"type\": \"function\", \"function\": {\"name\": \"my_function\"}} forces the model to call that tool.\n  none is the default when no tools are present. auto is the default if tools are present."},"normalize_tool_schemas":{"type":"boolean","description":"Enable provider compatibility normalization for tool function JSON schemas."},"parallel_tool_calls":{"type":"boolean","description":"Whether to enable parallel function calling during tool use."},"reasoning_effort":{"type":"string","enum":["minimal","low","medium","high","max"],"description":"Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response."},"router":{"type":"object","properties":{"decision_model":{"type":"string","enum":["typesafe/jev","liquid/d1"],"description":"The decision model that picks each request's bucket. Default `typesafe/jev`. Only decision models are accepted here, never a chat model. Every judgement is billed at that model's catalogue price and listed as its own request in your usage; turns that need none (tool results, a forced bucket, a single bucket) pay nothing for it."},"buckets":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","maxLength":32,"pattern":"^[A-Za-z0-9][A-Za-z0-9_.-]*$","description":"The bucket's name, unique in the router: 1 to 32 letters, digits, `-`, `_` or `.`. Name it in `default_bucket` and `force_bucket`; the response's `meta.router.bucket` says which one answered."},"when":{"type":"string","minLength":1,"maxLength":500,"description":"What the requests this bucket takes look like, in your words (1 to 500 characters) — for example \"unsolicited advertising, prize claims or phishing\". The decision model picks the bucket whose `when` fits each request best. Required on every bucket when there are two or more; a single bucket has none."},"models":{"type":"array","items":{"anyOf":[{"type":"string","description":"A chat model id, as you would pass it in `model` (see `GET /v1/models`)."},{"type":"object","properties":{"model":{"type":"string"}},"required":["model"],"additionalProperties":false,"description":"The same model id, as an object: `{ \"model\": \"<id>\" }`."}],"description":"A chat model this bucket may answer with."},"maxItems":5,"description":"1 to 5 chat models, in the order to try them: the first one that can take the request (its tools, images, JSON schema and context size) answers, and if it fails the next one does. Only chat models we serve — not routers, not decision models. Models you list run with your request's own settings, reasoning included. Or none (`[]`): a request the decision model puts in this bucket ends at the decision — no model is called, and the response is an empty assistant message (`content: \"\"`, `finish_reason: \"stop\"`) whose `meta.router` says `\"routed\": false` and names the bucket, so your code acts on it. Only the judgement is charged. Not on a single bucket, which is never judged."}},"required":["name","models"],"additionalProperties":false,"description":"One bucket: its name, what it takes, and its models."},"minItems":1,"maxItems":10,"description":"Your buckets, 1 to 10: they replace the default buckets entirely. With two or more, each needs a `when`, and the decision model picks the one that fits each request. A single bucket is a fallback chain — every request goes to it, with no judgement. Left out: the default buckets — `light` (\"Needs little capability: greetings and small talk, one-line or lookup answers, common knowledge, short routine tasks such as a short piece of writing, a quick rewrite or simple arithmetic — a small, fast model answers it well\"): `openai/gpt-6-luna`, `deepseek/deepseek-v4.1-flash`, `google/gemini-3-1-flash-lite`, `google/gemini-3-5-flash-lite`; `standard` (\"Needs a capable model: multi-step tasks that need care and accuracy\"): `openai/gpt-6.1-sol`, `anthropic/claude-sonnet-5.5`; `heavy` (\"Needs the strongest model: complex reasoning, hard math or proofs, large or tricky code, expert-level or research-grade knowledge\"): `anthropic/claude-opus-5.5`, `openai/gpt-6-astra`."},"default_bucket":{"type":"string","description":"Where a request goes when it is not judged — the decision model failed, timed out or named no bucket, or the request has no text — and where one goes when none of its bucket's models can take it, before the others are tried. Default: your first bucket; `standard` for the default buckets. Required when your first bucket lists no models: a request that is not judged would otherwise end there, unanswered by any model."},"force_bucket":{"type":"string","description":"Send the request to this bucket without judging it (nothing is charged for a judgement)."},"min_confidence":{"type":"number","minimum":0,"maximum":1,"description":"Below this confidence in its answer (0 to 1), a request goes to `default_bucket` instead (`meta.router.reason`: `unsure`) — for example, send what the decision model is unsure about to your strongest bucket. The judgement is still paid for."}},"additionalProperties":false,"description":"How `aimlapi/dynamic-router` routes this request. Every setting is optional: left out, or `{}`, it routes like `typesafe/jev-router`; a setting you leave out keeps its default, and `buckets`, when given, are the whole table. A conversation stays on its model while its turns land in the same bucket; a turn returning tool results always goes back to the model that made the calls. The response says where the request went in `meta.router` (`routed`, bucket, reason, the decision model's choice and confidence, the judgement and its charge) and which model answered in `meta.model` — the router itself when the bucket lists no models. An invalid configuration is answered with a 400 that names each setting to fix, before anything is charged."}},"required":["model","messages"],"title":"aimlapi/dynamic-router"},{"type":"object","properties":{"model":{"type":"string","enum":["aimlapi/dynamic-router"]},"provider":{"type":"string","description":"Provider routing override. Use a source key such as `openai`, `openrouter`, `xai`, `google`, `alibaba`, `minimax`, `moonshot`, `baidu`, or `togetherai` to run that provider with no fallback; `auto` (default) uses the full fallback chain. Case-insensitive."},"messages":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"role":{"type":"string","enum":["user"],"description":"The role of the author of the message — in this case, the user"},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"type":{"type":"string","enum":["image_url"]},"image_url":{"type":"object","properties":{"url":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"}],"description":"Either a URL of the image or the base64 encoded image data. "},"detail":{"type":"string","enum":["low","high","auto"],"description":"Specifies the detail level of the image. Currently supports JPG/JPEG, PNG, GIF, and WEBP formats."}},"required":["url"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","image_url"]},{"type":"object","properties":{"type":{"type":"string","enum":["file"],"description":"The type of the content part."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]},"file":{"type":"object","properties":{"file_data":{"type":"string","description":"The file data, encoded in base64 and passed to the model as a string. Only PDF format is supported.\n        - Maximum size per file: Up to 512 MB and up to 2 million tokens.\n        - Maximum number of files: Up to 20 files can be attached to a single GPT application or Assistant. This limit applies throughout the application's lifetime.\n        - Maximum total file storage per user: 10 GB."},"file_id":{"type":"string"},"filename":{"type":"string","description":"The file name specified by the user. This name can be used to reference the file when interacting with the model, especially if multiple files are uploaded."}}}},"required":["type","file"]}]}}],"description":"The contents of the user message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the developer message."},"role":{"type":"string","enum":["developer"],"description":"The role of the author of the message — in this case, the developer."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["content","role"]},{"type":"object","properties":{"role":{"type":"string","enum":["system"],"description":"The role of the author of the message — in this case, the system."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the system message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"role":{"type":"string","enum":["tool"],"description":"The role of the author of the message — in this case, the tool."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the tool message."},"tool_call_id":{"type":"string","description":"Tool call that this message is responding to."},"name":{"type":"string","nullable":true,"description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content","tool_call_id"]},{"type":"object","properties":{"role":{"type":"string","enum":["assistant"],"description":"The role of the author of the message — in this case, the Assistant."},"content":{"anyOf":[{"type":"string","description":"The contents of the Assistant message."},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"refusal":{"type":"string","description":"The refusal message generated by the model."},"type":{"type":"string","enum":["refusal"],"description":"The type of the content part."}},"required":["refusal","type"]}]},"description":"An array of content parts with a defined type. Can be one or more of type text, or exactly one of type refusal."},{"nullable":true}],"description":"The contents of the Assistant message. Required unless tool_calls or function_call is specified."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."},"tool_calls":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."},"arguments":{"type":"string","description":"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."}},"required":["name","arguments"],"description":"The function that the model called."},"extra_content":{"type":"object","additionalProperties":{"nullable":true},"description":"Opaque provider metadata for this tool call (e.g. Gemini thought_signature). Echo it back unchanged on the next turn."}},"required":["id","type","function"]},{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool to call."},"input":{"type":"string","description":"The input for the custom tool call generated by the model."}},"required":["name","input"],"description":"The custom tool that the model called."},"extra_content":{"type":"object","additionalProperties":{"nullable":true},"description":"Opaque provider metadata for this tool call (e.g. Gemini thought_signature). Echo it back unchanged on the next turn."}},"required":["id","type","custom"]}]},"description":"The tool calls generated by the model, such as function calls."},"refusal":{"type":"string","nullable":true,"description":"The refusal message by the Assistant."}},"required":["role"]}]},"description":"A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, documents (txt, pdf), images, and audio."},"max_tokens":{"type":"number","minimum":1,"description":"The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API."},"stream":{"type":"boolean","default":false,"description":"If set to True, the model response data will be streamed to the client as it is generated using server-sent events."},"stream_options":{"type":"object","properties":{"include_usage":{"type":"boolean"}},"required":["include_usage"]},"tools":{"type":"array","items":{"anyOf":[{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"description":{"type":"string","description":"A description of what the function does, used by the model to choose when and how to call the function."},"name":{"type":"string","description":"The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."},"parameters":{"type":"object","additionalProperties":{"nullable":true,"description":"The parameters the functions accepts, described as a JSON Schema object."}},"strict":{"type":"boolean","nullable":true,"description":"Whether to enable strict schema adherence when generating the function call. If set to True, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is True."}},"required":["name"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","function"]},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool, used to identify it in tool calls."},"description":{"type":"string","description":"Optional description of the custom tool, used to provide more context."},"format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["grammar"]},"grammar":{"type":"object","properties":{"definition":{"type":"string","description":"The grammar definition."},"syntax":{"type":"string","enum":["lark","regex"],"description":"The syntax of the grammar definition."}},"required":["definition","syntax"]}},"required":["type","grammar"]}],"description":"The input format for the custom tool. Default is unconstrained text."}},"required":["name","format"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","custom"]}]},{"type":"object","properties":{"type":{"type":"string","minLength":1}},"required":["type"]}]},"description":"A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported."},"tool_choice":{"anyOf":[{"type":"string","enum":["none","auto","required"],"description":"none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."}},"required":["name"]}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["allowed_tools"],"description":"The type of the tool. Currently, only function is supported."},"allowed_tools":{"type":"object","properties":{"mode":{"type":"string","enum":["auto","required"],"description":"Constrains the tools available to the model to a pre-defined set.\n- auto allows the model to pick from among the allowed tools and generate a message.\n- required requires the model to call one or more of the allowed tools."},"tools":{"type":"array","items":{"type":"object","additionalProperties":{"nullable":true}},"description":"A list of tool definitions that the model should be allowed to call."}},"required":["mode","tools"]}},"required":["type","allowed_tools"],"description":"Constrains the tools available to the model to a pre-defined set."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"string","enum":["name"],"description":"The name of the function to call."}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"string","enum":["name"],"description":"The name of the custom tool to call."}},"required":["type","custom"],"description":"Specifies a tool the model should use. Use to force the model to call a specific custom tool."}],"description":"Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {\"type\": \"function\", \"function\": {\"name\": \"my_function\"}} forces the model to call that tool.\n  none is the default when no tools are present. auto is the default if tools are present."},"normalize_tool_schemas":{"type":"boolean","description":"Enable provider compatibility normalization for tool function JSON schemas."},"parallel_tool_calls":{"type":"boolean","description":"Whether to enable parallel function calling during tool use."},"n":{"type":"integer","nullable":true,"minimum":1,"description":"How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs."},"seed":{"type":"integer","minimum":1,"description":"This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result."},"reasoning_effort":{"type":"string","enum":["low","medium","high"],"description":"Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response."},"response_format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of response format being defined. Always text."}},"required":["type"],"additionalProperties":false,"description":"Default response format. Used to generate text responses."},{"type":"object","properties":{"type":{"type":"string","enum":["json_object"],"description":"The type of response format being defined. Always json_object."}},"required":["type"],"additionalProperties":false,"description":"An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema"],"description":"The type of response format being defined. Always json_schema."},"json_schema":{"type":"object","properties":{"name":{"type":"string","description":"The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."},"schema":{"type":"object","additionalProperties":{"nullable":true},"description":"The schema for the response format, described as a JSON Schema object."},"strict":{"type":"boolean","nullable":true,"description":"Whether to enable strict schema adherence when generating the output. If set to True, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is True."},"description":{"type":"string","description":"A description of what the response format is for, used by the model to determine how to respond in the format."}},"required":["name"],"additionalProperties":false,"description":"JSON Schema response format. Used to generate structured JSON responses."}},"required":["type","json_schema"],"additionalProperties":false,"description":"JSON Schema response format. Used to generate structured JSON responses."}],"description":"An object specifying the format that the model must output."},"router":{"type":"object","properties":{"decision_model":{"type":"string","enum":["typesafe/jev","liquid/d1"],"description":"The decision model that picks each request's bucket. Default `typesafe/jev`. Only decision models are accepted here, never a chat model. Every judgement is billed at that model's catalogue price and listed as its own request in your usage; turns that need none (tool results, a forced bucket, a single bucket) pay nothing for it."},"buckets":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","maxLength":32,"pattern":"^[A-Za-z0-9][A-Za-z0-9_.-]*$","description":"The bucket's name, unique in the router: 1 to 32 letters, digits, `-`, `_` or `.`. Name it in `default_bucket` and `force_bucket`; the response's `meta.router.bucket` says which one answered."},"when":{"type":"string","minLength":1,"maxLength":500,"description":"What the requests this bucket takes look like, in your words (1 to 500 characters) — for example \"unsolicited advertising, prize claims or phishing\". The decision model picks the bucket whose `when` fits each request best. Required on every bucket when there are two or more; a single bucket has none."},"models":{"type":"array","items":{"anyOf":[{"type":"string","description":"A chat model id, as you would pass it in `model` (see `GET /v1/models`)."},{"type":"object","properties":{"model":{"type":"string"}},"required":["model"],"additionalProperties":false,"description":"The same model id, as an object: `{ \"model\": \"<id>\" }`."}],"description":"A chat model this bucket may answer with."},"maxItems":5,"description":"1 to 5 chat models, in the order to try them: the first one that can take the request (its tools, images, JSON schema and context size) answers, and if it fails the next one does. Only chat models we serve — not routers, not decision models. Models you list run with your request's own settings, reasoning included. Or none (`[]`): a request the decision model puts in this bucket ends at the decision — no model is called, and the response is an empty assistant message (`content: \"\"`, `finish_reason: \"stop\"`) whose `meta.router` says `\"routed\": false` and names the bucket, so your code acts on it. Only the judgement is charged. Not on a single bucket, which is never judged."}},"required":["name","models"],"additionalProperties":false,"description":"One bucket: its name, what it takes, and its models."},"minItems":1,"maxItems":10,"description":"Your buckets, 1 to 10: they replace the default buckets entirely. With two or more, each needs a `when`, and the decision model picks the one that fits each request. A single bucket is a fallback chain — every request goes to it, with no judgement. Left out: the default buckets — `light` (\"Needs little capability: greetings and small talk, one-line or lookup answers, common knowledge, short routine tasks such as a short piece of writing, a quick rewrite or simple arithmetic — a small, fast model answers it well\"): `openai/gpt-6-luna`, `deepseek/deepseek-v4.1-flash`, `google/gemini-3-1-flash-lite`, `google/gemini-3-5-flash-lite`; `standard` (\"Needs a capable model: multi-step tasks that need care and accuracy\"): `openai/gpt-6.1-sol`, `anthropic/claude-sonnet-5.5`; `heavy` (\"Needs the strongest model: complex reasoning, hard math or proofs, large or tricky code, expert-level or research-grade knowledge\"): `anthropic/claude-opus-5.5`, `openai/gpt-6-astra`."},"default_bucket":{"type":"string","description":"Where a request goes when it is not judged — the decision model failed, timed out or named no bucket, or the request has no text — and where one goes when none of its bucket's models can take it, before the others are tried. Default: your first bucket; `standard` for the default buckets. Required when your first bucket lists no models: a request that is not judged would otherwise end there, unanswered by any model."},"force_bucket":{"type":"string","description":"Send the request to this bucket without judging it (nothing is charged for a judgement)."},"min_confidence":{"type":"number","minimum":0,"maximum":1,"description":"Below this confidence in its answer (0 to 1), a request goes to `default_bucket` instead (`meta.router.reason`: `unsure`) — for example, send what the decision model is unsure about to your strongest bucket. The judgement is still paid for."}},"additionalProperties":false,"description":"How `aimlapi/dynamic-router` routes this request. Every setting is optional: left out, or `{}`, it routes like `typesafe/jev-router`; a setting you leave out keeps its default, and `buckets`, when given, are the whole table. A conversation stays on its model while its turns land in the same bucket; a turn returning tool results always goes back to the model that made the calls. The response says where the request went in `meta.router` (`routed`, bucket, reason, the decision model's choice and confidence, the judgement and its charge) and which model answered in `meta.model` — the router itself when the bucket lists no models. An invalid configuration is answered with a 400 that names each setting to fix, before anything is charged."}},"required":["model","messages"],"title":"aimlapi/dynamic-router"},{"type":"object","properties":{"model":{"type":"string","enum":["aimlapi/dynamic-router"]},"messages":{"anyOf":[{"type":"array","items":{"oneOf":[{"type":"object","properties":{"role":{"type":"string","enum":["user","assistant"]},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"type":{"type":"string","enum":["image"]},"source":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["base64"],"description":"The type of the image."},"media_type":{"type":"string","enum":["image/jpeg","image/png","image/gif","image/webp"],"description":"The media type of the image."},"data":{"type":"string","description":"The base64 encoded image data."}},"required":["type","media_type","data"]},{"type":"object","properties":{"type":{"type":"string","enum":["url"]},"url":{"type":"string","format":"uri"}},"required":["type","url"]}]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","source"]},{"type":"object","properties":{"type":{"type":"string","enum":["thinking"]},"thinking":{"type":"string"},"signature":{"type":"string"}},"required":["type","thinking","signature"]},{"type":"object","properties":{"type":{"type":"string","enum":["tool_result"]},"tool_use_id":{"type":"string"},"is_error":{"type":"boolean"},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"type":{"type":"string","enum":["image"]},"source":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["base64"],"description":"The type of the image."},"media_type":{"type":"string","enum":["image/jpeg","image/png","image/gif","image/webp"],"description":"The media type of the image."},"data":{"type":"string","description":"The base64 encoded image data."}},"required":["type","media_type","data"]},{"type":"object","properties":{"type":{"type":"string","enum":["url"]},"url":{"type":"string","format":"uri"}},"required":["type","url"]}]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","source"]},{"type":"object","properties":{"type":{"type":"string","enum":["search_result"]},"source":{"type":"string"},"title":{"type":"string"},"content":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","source","title","content"]},{"type":"object","properties":{"type":{"type":"string","enum":["document"]},"source":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["base64"]},"media_type":{"type":"string","enum":["application/pdf","text/plain"]},"data":{"type":"string"}},"required":["type","media_type","data"]},{"type":"object","properties":{"type":{"type":"string","enum":["text"]},"media_type":{"type":"string","enum":["text/plain"]},"data":{"type":"string"}},"required":["type","media_type","data"]},{"type":"object","properties":{"type":{"type":"string","enum":["url"]},"url":{"type":"string","format":"uri"}},"required":["type","url"]},{"type":"object","properties":{"type":{"type":"string","enum":["content"]},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"nullable":true}}]}},"required":["type","content"]}]},"title":{"type":"string"},"context":{"type":"string"},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","source"]},{"type":"object","properties":{"type":{"type":"string","enum":["tool_reference"]},"tool_name":{"type":"string"},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","tool_name"]}]}}]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","tool_use_id"]},{"type":"object","properties":{"type":{"type":"string","enum":["tool_use"]},"id":{"type":"string"},"name":{"type":"string"},"input":{"type":"object","additionalProperties":{"nullable":true}},"caller":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["direct"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["code_execution_20250825"]},"tool_id":{"type":"string"}},"required":["type","tool_id"]},{"type":"object","properties":{"type":{"type":"string","enum":["code_execution_20260120"]},"tool_id":{"type":"string"}},"required":["type","tool_id"]}]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","id","name","input"]},{"type":"object","properties":{"type":{"type":"string","enum":["server_tool_use"]},"id":{"type":"string"},"name":{"type":"string","enum":["web_search","web_fetch","code_execution","bash_code_execution","text_editor_code_execution","tool_search_tool_regex","tool_search_tool_bm25"]},"input":{"type":"object","additionalProperties":{"nullable":true}},"caller":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["direct"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["code_execution_20250825"]},"tool_id":{"type":"string"}},"required":["type","tool_id"]},{"type":"object","properties":{"type":{"type":"string","enum":["code_execution_20260120"]},"tool_id":{"type":"string"}},"required":["type","tool_id"]}]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","id","name","input"]},{"type":"object","properties":{"type":{"type":"string","enum":["search_result"]},"source":{"type":"string"},"title":{"type":"string"},"content":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","source","title","content"]},{"type":"object","properties":{"type":{"type":"string","enum":["web_search_tool_result"]},"tool_use_id":{"type":"string"},"content":{"anyOf":[{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["web_search_result"]},"title":{"type":"string"},"url":{"type":"string"},"page_age":{"type":"string"},"encrypted_content":{"type":"string"}},"required":["type","title","url","encrypted_content"]}},{"type":"object","properties":{"type":{"type":"string","enum":["web_search_tool_result_error"]},"error_code":{"type":"string","enum":["invalid_tool_input","unavailable","max_uses_exceeded","too_many_requests","query_too_long","request_too_large"]}},"required":["type","error_code"]}]},"caller":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["direct"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["code_execution_20250825"]},"tool_id":{"type":"string"}},"required":["type","tool_id"]},{"type":"object","properties":{"type":{"type":"string","enum":["code_execution_20260120"]},"tool_id":{"type":"string"}},"required":["type","tool_id"]}]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","tool_use_id","content"]},{"type":"object","properties":{"type":{"type":"string","enum":["web_fetch_tool_result"]},"tool_use_id":{"type":"string"},"content":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["web_fetch_tool_result_error"]},"error_code":{"type":"string","enum":["invalid_tool_input","url_too_long","url_not_allowed","url_not_accessible","unsupported_content_type","too_many_requests","max_uses_exceeded","unavailable"]}},"required":["type","error_code"]},{"type":"object","properties":{"type":{"type":"string","enum":["web_fetch_result"]},"url":{"type":"string"},"retrieved_at":{"type":"string"},"content":{"type":"object","properties":{"type":{"type":"string","enum":["document"]},"source":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["base64"]},"media_type":{"type":"string","enum":["application/pdf","text/plain"]},"data":{"type":"string"}},"required":["type","media_type","data"]},{"type":"object","properties":{"type":{"type":"string","enum":["text"]},"media_type":{"type":"string","enum":["text/plain"]},"data":{"type":"string"}},"required":["type","media_type","data"]},{"type":"object","properties":{"type":{"type":"string","enum":["url"]},"url":{"type":"string","format":"uri"}},"required":["type","url"]},{"type":"object","properties":{"type":{"type":"string","enum":["content"]},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"nullable":true}}]}},"required":["type","content"]}]},"title":{"type":"string"},"context":{"type":"string"},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","source"]}},"required":["type","url","content"]}]},"caller":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["direct"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["code_execution_20250825"]},"tool_id":{"type":"string"}},"required":["type","tool_id"]},{"type":"object","properties":{"type":{"type":"string","enum":["code_execution_20260120"]},"tool_id":{"type":"string"}},"required":["type","tool_id"]}]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","tool_use_id","content"]},{"type":"object","properties":{"type":{"type":"string","enum":["code_execution_tool_result"]},"tool_use_id":{"type":"string"},"content":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["code_execution_tool_result_error"]},"error_code":{"type":"string","enum":["invalid_tool_input","unavailable","too_many_requests","execution_time_exceeded"]}},"required":["type","error_code"]},{"type":"object","properties":{"type":{"type":"string","enum":["code_execution_result"]},"stdout":{"type":"string"},"stderr":{"type":"string"},"return_code":{"type":"number"},"content":{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["code_execution_output"]},"file_id":{"type":"string"}},"required":["type","file_id"]}}},"required":["type","stdout","stderr","return_code"]},{"type":"object","properties":{"type":{"type":"string","enum":["encrypted_code_execution_result"]},"encrypted_stdout":{"type":"string"},"stderr":{"type":"string"},"return_code":{"type":"number"},"content":{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["code_execution_output"]},"file_id":{"type":"string"}},"required":["type","file_id"]}}},"required":["type","encrypted_stdout","stderr","return_code"]}]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","tool_use_id","content"]},{"type":"object","properties":{"type":{"type":"string","enum":["bash_code_execution_tool_result"]},"tool_use_id":{"type":"string"},"content":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["bash_code_execution_tool_result_error"]},"error_code":{"type":"string","enum":["invalid_tool_input","unavailable","too_many_requests","execution_time_exceeded","output_file_too_large"]}},"required":["type","error_code"]},{"type":"object","properties":{"type":{"type":"string","enum":["bash_code_execution_result"]},"stdout":{"type":"string"},"stderr":{"type":"string"},"return_code":{"type":"number"},"content":{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["bash_code_execution_output"]},"file_id":{"type":"string"}},"required":["type","file_id"]}}},"required":["type","stdout","stderr","return_code"]}]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","tool_use_id","content"]},{"type":"object","properties":{"type":{"type":"string","enum":["text_editor_code_execution_tool_result"]},"tool_use_id":{"type":"string"},"content":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text_editor_code_execution_tool_result_error"]},"error_code":{"type":"string","enum":["invalid_tool_input","unavailable","too_many_requests","execution_time_exceeded","file_not_found"]},"error_message":{"type":"string"}},"required":["type","error_code"]},{"type":"object","properties":{"type":{"type":"string","enum":["text_editor_code_execution_view_result"]},"content":{"type":"string"},"file_type":{"type":"string","enum":["text","image","pdf"]},"start_line":{"type":"number"},"num_lines":{"type":"number"},"total_lines":{"type":"number"}},"required":["type","content","file_type"]},{"type":"object","properties":{"type":{"type":"string","enum":["text_editor_code_execution_create_result"]},"is_file_update":{"type":"boolean"}},"required":["type","is_file_update"]},{"type":"object","properties":{"type":{"type":"string","enum":["text_editor_code_execution_str_replace_result"]},"old_start":{"type":"number"},"old_lines":{"type":"number"},"new_start":{"type":"number"},"new_lines":{"type":"number"},"lines":{"type":"array","items":{"type":"string"}}},"required":["type"]}]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","tool_use_id","content"]},{"type":"object","properties":{"type":{"type":"string","enum":["tool_search_tool_result"]},"tool_use_id":{"type":"string"},"content":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["tool_search_tool_result_error"]},"error_code":{"type":"string","enum":["invalid_tool_input","unavailable","too_many_requests","execution_time_exceeded"]}},"required":["type","error_code"]},{"type":"object","properties":{"type":{"type":"string","enum":["tool_search_tool_search_result"]},"tool_references":{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["tool_reference"]},"tool_name":{"type":"string"},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","tool_name"]}}},"required":["type","tool_references"]}]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","tool_use_id","content"]},{"type":"object","properties":{"type":{"type":"string","enum":["redacted_thinking"]},"data":{"type":"string"}},"required":["type","data"]},{"type":"object","properties":{"type":{"type":"string","enum":["document"]},"source":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["base64"]},"media_type":{"type":"string","enum":["application/pdf","text/plain"]},"data":{"type":"string"}},"required":["type","media_type","data"]},{"type":"object","properties":{"type":{"type":"string","enum":["text"]},"media_type":{"type":"string","enum":["text/plain"]},"data":{"type":"string"}},"required":["type","media_type","data"]},{"type":"object","properties":{"type":{"type":"string","enum":["url"]},"url":{"type":"string","format":"uri"}},"required":["type","url"]},{"type":"object","properties":{"type":{"type":"string","enum":["content"]},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"nullable":true}}]}},"required":["type","content"]}]},"title":{"type":"string"},"context":{"type":"string"},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","source"]}]}}]}},"required":["role","content"]},{"type":"object","properties":{"role":{"type":"string","enum":["system"]},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}]}},"required":["role","content"]}]}},{"type":"array","items":{"oneOf":[{"type":"object","properties":{"role":{"type":"string","enum":["system"],"description":"The role of the author of the message — in this case, the system."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the system message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"role":{"type":"string","enum":["user"],"description":"The role of the author of the message — in this case, the user"},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["image_url"]},"image_url":{"type":"object","properties":{"url":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"}],"description":"Either a URL of the image or the base64 encoded image data. "},"detail":{"type":"string","enum":["low","high","auto"],"description":"Specifies the detail level of the image. Currently supports JPG/JPEG, PNG, GIF, and WEBP formats."}},"required":["url"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","image_url"]},{"type":"object","properties":{"type":{"type":"string","enum":["image"]},"source":{"type":"object","properties":{"type":{"type":"string","enum":["base64"]},"media_type":{"type":"string","enum":["image/jpeg","image/png","image/gif","image/webp"]},"data":{"type":"string"}},"required":["type","media_type","data"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","source"]},{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"type":{"type":"string","enum":["input_audio"],"description":"The type of the content part."},"input_audio":{"type":"object","properties":{"data":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"},{"type":"string"}],"description":"Either a URL of the audio or the base64 encoded audio data."},"format":{"type":"string","enum":["wav","mp3","audio/x-aac","audio/flac","audio/mp3","audio/m4a","audio/mpeg","audio/mpga","audio/mp4","audio/ogg","audio/pcm","audio/webm"],"description":"The format of the encoded audio data. Currently supports \"wav\" and \"mp3\"."}},"required":["data","format"]}},"required":["type","input_audio"]},{"type":"object","properties":{"type":{"type":"string","enum":["file"],"description":"The type of the content part."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]},"file":{"type":"object","properties":{"file_data":{"type":"string","description":"The file data, encoded in base64 and passed to the model as a string. Only PDF format is supported.\n        - Maximum size per file: Up to 512 MB and up to 2 million tokens.\n        - Maximum number of files: Up to 20 files can be attached to a single GPT application or Assistant. This limit applies throughout the application's lifetime.\n        - Maximum total file storage per user: 10 GB."},"file_id":{"type":"string"},"filename":{"type":"string","description":"The file name specified by the user. This name can be used to reference the file when interacting with the model, especially if multiple files are uploaded."}}}},"required":["type","file"]},{"type":"object","properties":{"type":{"type":"string","enum":["video_url"]},"video_url":{"type":"object","properties":{"url":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"}],"description":"Base64-encoded local video file."}},"required":["url"]}},"required":["type","video_url"]}]}}],"description":"The contents of the user message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"role":{"type":"string","enum":["tool"],"description":"The role of the author of the message — in this case, the tool."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the tool message."},"tool_call_id":{"type":"string","description":"Tool call that this message is responding to."},"name":{"type":"string","nullable":true,"description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content","tool_call_id"]},{"type":"object","properties":{"role":{"type":"string","enum":["function"]},"content":{"type":"string"},"name":{"type":"string"}},"required":["role","content","name"]},{"type":"object","properties":{"role":{"type":"string","enum":["assistant"],"description":"The role of the author of the message — in this case, the Assistant."},"content":{"anyOf":[{"type":"string","description":"The contents of the Assistant message."},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"refusal":{"type":"string","description":"The refusal message generated by the model."},"type":{"type":"string","enum":["refusal"],"description":"The type of the content part."}},"required":["refusal","type"]}]},"description":"An array of content parts with a defined type. Can be one or more of type text, or exactly one of type refusal."},{"nullable":true}],"description":"The contents of the Assistant message. Required unless tool_calls or function_call is specified."},"tool_calls":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."},"arguments":{"type":"string","description":"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."}},"required":["name","arguments"],"description":"The function that the model called."},"extra_content":{"type":"object","additionalProperties":{"nullable":true},"description":"Opaque provider metadata for this tool call (e.g. Gemini thought_signature). Echo it back unchanged on the next turn."}},"required":["id","type","function"]},{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool to call."},"input":{"type":"string","description":"The input for the custom tool call generated by the model."}},"required":["name","input"],"description":"The custom tool that the model called."},"extra_content":{"type":"object","additionalProperties":{"nullable":true},"description":"Opaque provider metadata for this tool call (e.g. Gemini thought_signature). Echo it back unchanged on the next turn."}},"required":["id","type","custom"]}]},"description":"The tool calls generated by the model, such as function calls."},"reasoning_content":{"type":"string"},"refusal":{"type":"string","nullable":true,"description":"The refusal message by the Assistant."},"audio":{"type":"object","nullable":true,"properties":{"id":{"type":"string","description":"Unique identifier for a previous audio response from the model."}},"required":["id"],"description":"Data about a previous audio response from the model."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role"]},{"type":"object","properties":{"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the developer message."},"role":{"type":"string","enum":["developer"],"description":"The role of the author of the message — in this case, the developer."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["content","role"]}]}}],"description":"A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, documents (txt, pdf), images, and audio."},"metadata":{"type":"object","additionalProperties":{"type":"string"},"description":"An object describing metadata about the request"},"stop_sequences":{"type":"array","items":{"type":"string"},"description":"Custom text sequences that will cause the model to stop generating."},"stream":{"type":"boolean","default":false,"description":"If set to True, the model response data will be streamed to the client as it is generated using server-sent events."},"system":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"default":"text"},"text":{"type":"string"},"citations":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["char_location"]},"cited_text":{"type":"string"},"document_index":{"type":"number"},"document_title":{"type":"string"},"end_char_index":{"type":"number"},"start_char_index":{"type":"number"}},"required":["type","cited_text","document_index","document_title","end_char_index","start_char_index"]},{"type":"object","properties":{"type":{"type":"string","enum":["page_location"]},"cited_text":{"type":"string"},"document_index":{"type":"number"},"document_title":{"type":"string"},"end_page_number":{"type":"number"},"start_page_number":{"type":"number"}},"required":["type","cited_text","document_index","document_title","end_page_number","start_page_number"]},{"type":"object","properties":{"type":{"type":"string","enum":["content_block_location"]},"cited_text":{"type":"string"},"document_index":{"type":"number"},"document_title":{"type":"string"},"end_block_index":{"type":"number"},"start_block_index":{"type":"number"}},"required":["type","cited_text","document_index","document_title","end_block_index","start_block_index"]},{"type":"object","properties":{"type":{"type":"string","enum":["web_search_result_location"]},"cited_text":{"type":"string"},"encrypted_index":{"type":"string"},"title":{"type":"string"},"url":{"type":"string"}},"required":["type","cited_text","encrypted_index","title","url"]},{"type":"object","properties":{"type":{"type":"string","enum":["search_result_location"]},"cited_text":{"type":"string"},"end_block_index":{"type":"number"},"search_result_index":{"type":"number"},"source":{"type":"string"},"start_block_index":{"type":"number"},"title":{"type":"string"}},"required":["type","cited_text","end_block_index","search_result_index","source","start_block_index","title"]}]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["text"]}}],"description":"A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role."},"tool_choice":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["auto"]},"disable_parallel_tool_use":{"type":"boolean"}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["any"]},"disable_parallel_tool_use":{"type":"boolean"}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string"},"type":{"type":"string","enum":["tool"]},"disable_parallel_tool_use":{"type":"boolean"}},"required":["name","type"]},{"type":"object","properties":{"type":{"type":"string","enum":["none"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","minLength":1}},"required":["type"]},{"type":"string","enum":["none","auto","required"],"description":"none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."}},"required":["name"]}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["allowed_tools"],"description":"The type of the tool. Currently, only function is supported."},"allowed_tools":{"type":"object","properties":{"mode":{"type":"string","enum":["auto","required"],"description":"Constrains the tools available to the model to a pre-defined set.\n- auto allows the model to pick from among the allowed tools and generate a message.\n- required requires the model to call one or more of the allowed tools."},"tools":{"type":"array","items":{"type":"object","additionalProperties":{"nullable":true}},"description":"A list of tool definitions that the model should be allowed to call."}},"required":["mode","tools"]}},"required":["type","allowed_tools"],"description":"Constrains the tools available to the model to a pre-defined set."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"string","enum":["name"],"description":"The name of the function to call."}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"string","enum":["name"],"description":"The name of the custom tool to call."}},"required":["type","custom"],"description":"Specifies a tool the model should use. Use to force the model to call a specific custom tool."}],"description":"Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {\"type\": \"function\", \"function\": {\"name\": \"my_function\"}} forces the model to call that tool.\n  none is the default when no tools are present. auto is the default if tools are present."},"tools":{"anyOf":[{"type":"array","items":{"anyOf":[{"oneOf":[{"type":"object","properties":{"name":{"type":"string","description":"Name of the tool."},"description":{"type":"string","description":"Description of what this tool does.\n  Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema."},"input_schema":{"type":"object","properties":{"type":{"type":"string","enum":["object"]},"properties":{"nullable":true},"required":{"type":"array","items":{"type":"string"}}},"required":["type"],"additionalProperties":{"nullable":true},"description":"JSON schema for this tool's input.\n  This defines the shape of the input that your tool accepts and that the model will produce."},"type":{"type":"string","enum":["custom"]},"defer_loading":{"type":"boolean"},"eager_input_streaming":{"type":"boolean"},"input_examples":{"type":"array","items":{"type":"object","additionalProperties":{"nullable":true}}},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["name","input_schema"]},{"type":"object","properties":{"name":{"type":"string","enum":["bash"],"default":"bash"},"type":{"type":"string","enum":["bash_20250124"]},"input_examples":{"type":"array","items":{"type":"object","additionalProperties":{"nullable":true}}},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string","enum":["code_execution"],"default":"code_execution"},"type":{"type":"string","enum":["code_execution_20250522"]},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string","enum":["code_execution"],"default":"code_execution"},"type":{"type":"string","enum":["code_execution_20250825"]},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string","enum":["code_execution"],"default":"code_execution"},"type":{"type":"string","enum":["code_execution_20260120"]},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string","enum":["memory"],"default":"memory"},"type":{"type":"string","enum":["memory_20250818"]},"input_examples":{"type":"array","items":{"type":"object","additionalProperties":{"nullable":true}}},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string","enum":["str_replace_editor"],"default":"str_replace_editor"},"type":{"type":"string","enum":["text_editor_20250124"]},"input_examples":{"type":"array","items":{"type":"object","additionalProperties":{"nullable":true}}},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string","enum":["str_replace_based_edit_tool"],"default":"str_replace_based_edit_tool"},"type":{"type":"string","enum":["text_editor_20250429"]},"input_examples":{"type":"array","items":{"type":"object","additionalProperties":{"nullable":true}}},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string","enum":["str_replace_based_edit_tool"],"default":"str_replace_based_edit_tool"},"type":{"type":"string","enum":["text_editor_20250728"]},"max_characters":{"type":"number"},"input_examples":{"type":"array","items":{"type":"object","additionalProperties":{"nullable":true}}},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string","enum":["web_search"],"default":"web_search"},"type":{"type":"string","enum":["web_search_20250305"]},"allowed_domains":{"type":"array","items":{"type":"string"}},"blocked_domains":{"type":"array","items":{"type":"string"}},"max_uses":{"type":"number"},"user_location":{"type":"object","properties":{"type":{"type":"string","enum":["approximate"]},"city":{"type":"string"},"country":{"type":"string"},"region":{"type":"string"},"timezone":{"type":"string"}},"required":["type"]},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string","enum":["web_search"],"default":"web_search"},"type":{"type":"string","enum":["web_search_20260209"]},"allowed_domains":{"type":"array","items":{"type":"string"}},"blocked_domains":{"type":"array","items":{"type":"string"}},"max_uses":{"type":"number"},"user_location":{"type":"object","properties":{"type":{"type":"string","enum":["approximate"]},"city":{"type":"string"},"country":{"type":"string"},"region":{"type":"string"},"timezone":{"type":"string"}},"required":["type"]},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string","enum":["web_fetch"],"default":"web_fetch"},"type":{"type":"string","enum":["web_fetch_20250910"]},"allowed_domains":{"type":"array","items":{"type":"string"}},"blocked_domains":{"type":"array","items":{"type":"string"}},"citations":{"type":"object","properties":{"enabled":{"type":"boolean"}}},"max_content_tokens":{"type":"number"},"max_uses":{"type":"number"},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string","enum":["web_fetch"],"default":"web_fetch"},"type":{"type":"string","enum":["web_fetch_20260209"]},"allowed_domains":{"type":"array","items":{"type":"string"}},"blocked_domains":{"type":"array","items":{"type":"string"}},"citations":{"type":"object","properties":{"enabled":{"type":"boolean"}}},"max_content_tokens":{"type":"number"},"max_uses":{"type":"number"},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string","enum":["web_fetch"],"default":"web_fetch"},"type":{"type":"string","enum":["web_fetch_20260309"]},"allowed_domains":{"type":"array","items":{"type":"string"}},"blocked_domains":{"type":"array","items":{"type":"string"}},"citations":{"type":"object","properties":{"enabled":{"type":"boolean"}}},"max_content_tokens":{"type":"number"},"max_uses":{"type":"number"},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string","enum":["tool_search_tool_bm25"],"default":"tool_search_tool_bm25"},"type":{"type":"string","enum":["tool_search_tool_bm25_20251119","tool_search_tool_bm25"]},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string","enum":["tool_search_tool_regex"],"default":"tool_search_tool_regex"},"type":{"type":"string","enum":["tool_search_tool_regex_20251119","tool_search_tool_regex"]},"defer_loading":{"type":"boolean"},"strict":{"type":"boolean"},"allowed_callers":{"type":"array","items":{"type":"string","enum":["direct","code_execution_20250825","code_execution_20260120"]}},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type"]}]},{"type":"object","properties":{"type":{"type":"string","minLength":1}},"required":["type"]}]}},{"type":"array","items":{"anyOf":[{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"description":{"type":"string","description":"A description of what the function does, used by the model to choose when and how to call the function."},"name":{"type":"string","description":"The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."},"parameters":{"type":"object","additionalProperties":{"nullable":true,"description":"The parameters the functions accepts, described as a JSON Schema object."}},"strict":{"type":"boolean","nullable":true,"description":"Whether to enable strict schema adherence when generating the function call. If set to True, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is True."}},"required":["name"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","function"]},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool, used to identify it in tool calls."},"description":{"type":"string","description":"Optional description of the custom tool, used to provide more context."},"format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["grammar"]},"grammar":{"type":"object","properties":{"definition":{"type":"string","description":"The grammar definition."},"syntax":{"type":"string","enum":["lark","regex"],"description":"The syntax of the grammar definition."}},"required":["definition","syntax"]}},"required":["type","grammar"]}],"description":"The input format for the custom tool. Default is unconstrained text."}},"required":["name","format"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","custom"]}]},{"type":"object","properties":{"type":{"type":"string","minLength":1}},"required":["type"]}]}}],"description":"Definitions of tools that the model may use.\n  If you include tools in your API request, the model may return tool_use content blocks that represent the model's use of those tools. You can then run those tools using the tool input generated by the model and then optionally return results back to the model using tool_result content blocks.\n  Each tool definition includes:\n      name: Name of the tool.\n      description: Optional, but strongly-recommended description of the tool.\n      input_schema: JSON schema for the tool input shape that the model will produce in tool_use output content blocks."},"thinking":{"anyOf":[{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["enabled"]},"budget_tokens":{"type":"integer","minimum":1024,"description":"Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than max_tokens."},"display":{"type":"string","enum":["summarized","omitted"],"default":"summarized"}},"required":["type","budget_tokens"]},{"type":"object","properties":{"type":{"type":"string","enum":["disabled"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["adaptive"]},"display":{"type":"string","enum":["summarized","omitted"],"default":"summarized"}},"required":["type"]}]},{"type":"object","properties":{"type":{"type":"string","minLength":1}},"required":["type"]}],"description":"Configuration for enabling Claude's extended thinking. When enabled, responses include thinking content blocks showing Claude's thinking process before the final answer. Requires a minimum budget of 1,024 tokens and counts towards your max_tokens limit."},"max_tokens":{"type":"number","default":128000,"description":"The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API."},"reasoning_effort":{"type":"string","enum":["none","low","medium","high","xhigh","max"],"description":"Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response."},"router":{"type":"object","properties":{"decision_model":{"type":"string","enum":["typesafe/jev","liquid/d1"],"description":"The decision model that picks each request's bucket. Default `typesafe/jev`. Only decision models are accepted here, never a chat model. Every judgement is billed at that model's catalogue price and listed as its own request in your usage; turns that need none (tool results, a forced bucket, a single bucket) pay nothing for it."},"buckets":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","maxLength":32,"pattern":"^[A-Za-z0-9][A-Za-z0-9_.-]*$","description":"The bucket's name, unique in the router: 1 to 32 letters, digits, `-`, `_` or `.`. Name it in `default_bucket` and `force_bucket`; the response's `meta.router.bucket` says which one answered."},"when":{"type":"string","minLength":1,"maxLength":500,"description":"What the requests this bucket takes look like, in your words (1 to 500 characters) — for example \"unsolicited advertising, prize claims or phishing\". The decision model picks the bucket whose `when` fits each request best. Required on every bucket when there are two or more; a single bucket has none."},"models":{"type":"array","items":{"anyOf":[{"type":"string","description":"A chat model id, as you would pass it in `model` (see `GET /v1/models`)."},{"type":"object","properties":{"model":{"type":"string"}},"required":["model"],"additionalProperties":false,"description":"The same model id, as an object: `{ \"model\": \"<id>\" }`."}],"description":"A chat model this bucket may answer with."},"maxItems":5,"description":"1 to 5 chat models, in the order to try them: the first one that can take the request (its tools, images, JSON schema and context size) answers, and if it fails the next one does. Only chat models we serve — not routers, not decision models. Models you list run with your request's own settings, reasoning included. Or none (`[]`): a request the decision model puts in this bucket ends at the decision — no model is called, and the response is an empty assistant message (`content: \"\"`, `finish_reason: \"stop\"`) whose `meta.router` says `\"routed\": false` and names the bucket, so your code acts on it. Only the judgement is charged. Not on a single bucket, which is never judged."}},"required":["name","models"],"additionalProperties":false,"description":"One bucket: its name, what it takes, and its models."},"minItems":1,"maxItems":10,"description":"Your buckets, 1 to 10: they replace the default buckets entirely. With two or more, each needs a `when`, and the decision model picks the one that fits each request. A single bucket is a fallback chain — every request goes to it, with no judgement. Left out: the default buckets — `light` (\"Needs little capability: greetings and small talk, one-line or lookup answers, common knowledge, short routine tasks such as a short piece of writing, a quick rewrite or simple arithmetic — a small, fast model answers it well\"): `openai/gpt-6-luna`, `deepseek/deepseek-v4.1-flash`, `google/gemini-3-1-flash-lite`, `google/gemini-3-5-flash-lite`; `standard` (\"Needs a capable model: multi-step tasks that need care and accuracy\"): `openai/gpt-6.1-sol`, `anthropic/claude-sonnet-5.5`; `heavy` (\"Needs the strongest model: complex reasoning, hard math or proofs, large or tricky code, expert-level or research-grade knowledge\"): `anthropic/claude-opus-5.5`, `openai/gpt-6-astra`."},"default_bucket":{"type":"string","description":"Where a request goes when it is not judged — the decision model failed, timed out or named no bucket, or the request has no text — and where one goes when none of its bucket's models can take it, before the others are tried. Default: your first bucket; `standard` for the default buckets. Required when your first bucket lists no models: a request that is not judged would otherwise end there, unanswered by any model."},"force_bucket":{"type":"string","description":"Send the request to this bucket without judging it (nothing is charged for a judgement)."},"min_confidence":{"type":"number","minimum":0,"maximum":1,"description":"Below this confidence in its answer (0 to 1), a request goes to `default_bucket` instead (`meta.router.reason`: `unsure`) — for example, send what the decision model is unsure about to your strongest bucket. The judgement is still paid for."}},"additionalProperties":false,"description":"How `aimlapi/dynamic-router` routes this request. Every setting is optional: left out, or `{}`, it routes like `typesafe/jev-router`; a setting you leave out keeps its default, and `buckets`, when given, are the whole table. A conversation stays on its model while its turns land in the same bucket; a turn returning tool results always goes back to the model that made the calls. The response says where the request went in `meta.router` (`routed`, bucket, reason, the decision model's choice and confidence, the judgement and its charge) and which model answered in `meta.model` — the router itself when the bucket lists no models. An invalid configuration is answered with a 400 that names each setting to fix, before anything is charged."}},"required":["model","messages"],"title":"aimlapi/dynamic-router"},{"type":"object","properties":{"model":{"type":"string","enum":["aimlapi/dynamic-router"]},"provider":{"type":"string","description":"Provider routing override. Use a source key such as `openai`, `openrouter`, `xai`, `google`, `alibaba`, `minimax`, `moonshot`, `baidu`, or `togetherai` to run that provider with no fallback; `auto` (default) uses the full fallback chain. Case-insensitive."},"messages":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"role":{"type":"string","enum":["user"],"description":"The role of the author of the message — in this case, the user"},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"type":{"type":"string","enum":["image_url"]},"image_url":{"type":"object","properties":{"url":{"anyOf":[{"type":"string","format":"uri"},{"type":"string"}],"description":"Either a URL of the image or the base64 encoded image data. "},"detail":{"type":"string","enum":["low","high","auto"],"description":"Specifies the detail level of the image. Currently supports JPG/JPEG, PNG, GIF, and WEBP formats."}},"required":["url"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","image_url"]},{"type":"object","properties":{"type":{"type":"string","enum":["file"],"description":"The type of the content part."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]},"file":{"type":"object","properties":{"file_data":{"type":"string","description":"The file data, encoded in base64 and passed to the model as a string. Only PDF format is supported.\n        - Maximum size per file: Up to 512 MB and up to 2 million tokens.\n        - Maximum number of files: Up to 20 files can be attached to a single GPT application or Assistant. This limit applies throughout the application's lifetime.\n        - Maximum total file storage per user: 10 GB."},"file_id":{"type":"string"},"filename":{"type":"string","description":"The file name specified by the user. This name can be used to reference the file when interacting with the model, especially if multiple files are uploaded."}}}},"required":["type","file"]}]}}],"description":"The contents of the user message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the developer message."},"role":{"type":"string","enum":["developer"],"description":"The role of the author of the message — in this case, the developer."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["content","role"]},{"type":"object","properties":{"role":{"type":"string","enum":["system"],"description":"The role of the author of the message — in this case, the system."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the system message."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content"]},{"type":"object","properties":{"role":{"type":"string","enum":["tool"],"description":"The role of the author of the message — in this case, the tool."},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]}}],"description":"The contents of the tool message."},"tool_call_id":{"type":"string","description":"Tool call that this message is responding to."},"name":{"type":"string","nullable":true,"description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."}},"required":["role","content","tool_call_id"]},{"type":"object","properties":{"role":{"type":"string","enum":["assistant"],"description":"The role of the author of the message — in this case, the Assistant."},"content":{"anyOf":[{"type":"string","description":"The contents of the Assistant message."},{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of the content part."},"text":{"type":"string","description":"The text content."},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","text"]},{"type":"object","properties":{"refusal":{"type":"string","description":"The refusal message generated by the model."},"type":{"type":"string","enum":["refusal"],"description":"The type of the content part."}},"required":["refusal","type"]}]},"description":"An array of content parts with a defined type. Can be one or more of type text, or exactly one of type refusal."},{"nullable":true}],"description":"The contents of the Assistant message. Required unless tool_calls or function_call is specified."},"name":{"type":"string","description":"An optional name for the participant. Provides the model information to differentiate between participants of the same role."},"tool_calls":{"type":"array","items":{"oneOf":[{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."},"arguments":{"type":"string","description":"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."}},"required":["name","arguments"],"description":"The function that the model called."},"extra_content":{"type":"object","additionalProperties":{"nullable":true},"description":"Opaque provider metadata for this tool call (e.g. Gemini thought_signature). Echo it back unchanged on the next turn."}},"required":["id","type","function"]},{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool to call."},"input":{"type":"string","description":"The input for the custom tool call generated by the model."}},"required":["name","input"],"description":"The custom tool that the model called."},"extra_content":{"type":"object","additionalProperties":{"nullable":true},"description":"Opaque provider metadata for this tool call (e.g. Gemini thought_signature). Echo it back unchanged on the next turn."}},"required":["id","type","custom"]}]},"description":"The tool calls generated by the model, such as function calls."},"refusal":{"type":"string","nullable":true,"description":"The refusal message by the Assistant."}},"required":["role"]}]},"description":"A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, documents (txt, pdf), images, and audio."},"max_tokens":{"type":"number","minimum":1,"description":"The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API."},"stream":{"type":"boolean","default":false,"description":"If set to True, the model response data will be streamed to the client as it is generated using server-sent events."},"stream_options":{"type":"object","properties":{"include_usage":{"type":"boolean"}},"required":["include_usage"]},"tools":{"type":"array","items":{"anyOf":[{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"description":{"type":"string","description":"A description of what the function does, used by the model to choose when and how to call the function."},"name":{"type":"string","description":"The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."},"parameters":{"type":"object","additionalProperties":{"nullable":true,"description":"The parameters the functions accepts, described as a JSON Schema object."}},"strict":{"type":"boolean","nullable":true,"description":"Whether to enable strict schema adherence when generating the function call. If set to True, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is True."}},"required":["name"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","function"]},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"object","properties":{"name":{"type":"string","description":"The name of the custom tool, used to identify it in tool calls."},"description":{"type":"string","description":"Optional description of the custom tool, used to provide more context."},"format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["grammar"]},"grammar":{"type":"object","properties":{"definition":{"type":"string","description":"The grammar definition."},"syntax":{"type":"string","enum":["lark","regex"],"description":"The syntax of the grammar definition."}},"required":["definition","syntax"]}},"required":["type","grammar"]}],"description":"The input format for the custom tool. Default is unconstrained text."}},"required":["name","format"]},"cache_control":{"type":"object","properties":{"type":{"type":"string","enum":["ephemeral"]},"ttl":{"type":"string","enum":["5m","1h"]}},"required":["type"]}},"required":["type","custom"]}]},{"type":"object","properties":{"type":{"type":"string","minLength":1}},"required":["type"]}]},"description":"A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported."},"tool_choice":{"anyOf":[{"type":"string","enum":["none","auto","required"],"description":"none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"object","properties":{"name":{"type":"string","description":"The name of the function to call."}},"required":["name"]}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["allowed_tools"],"description":"The type of the tool. Currently, only function is supported."},"allowed_tools":{"type":"object","properties":{"mode":{"type":"string","enum":["auto","required"],"description":"Constrains the tools available to the model to a pre-defined set.\n- auto allows the model to pick from among the allowed tools and generate a message.\n- required requires the model to call one or more of the allowed tools."},"tools":{"type":"array","items":{"type":"object","additionalProperties":{"nullable":true}},"description":"A list of tool definitions that the model should be allowed to call."}},"required":["mode","tools"]}},"required":["type","allowed_tools"],"description":"Constrains the tools available to the model to a pre-defined set."},{"type":"object","properties":{"type":{"type":"string","enum":["function"],"description":"The type of the tool. Currently, only function is supported."},"function":{"type":"string","enum":["name"],"description":"The name of the function to call."}},"required":["type","function"],"description":"Specifies a tool the model should use. Use to force the model to call a specific function."},{"type":"object","properties":{"type":{"type":"string","enum":["custom"],"description":"The type of the tool. Currently, only function is supported."},"custom":{"type":"string","enum":["name"],"description":"The name of the custom tool to call."}},"required":["type","custom"],"description":"Specifies a tool the model should use. Use to force the model to call a specific custom tool."}],"description":"Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {\"type\": \"function\", \"function\": {\"name\": \"my_function\"}} forces the model to call that tool.\n  none is the default when no tools are present. auto is the default if tools are present."},"normalize_tool_schemas":{"type":"boolean","description":"Enable provider compatibility normalization for tool function JSON schemas."},"parallel_tool_calls":{"type":"boolean","description":"Whether to enable parallel function calling during tool use."},"n":{"type":"integer","nullable":true,"minimum":1,"description":"How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs."},"seed":{"type":"integer","minimum":1,"description":"This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result."},"reasoning_effort":{"type":"string","enum":["low","medium","high","xhigh"],"description":"Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response."},"response_format":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["text"],"description":"The type of response format being defined. Always text."}},"required":["type"],"additionalProperties":false,"description":"Default response format. Used to generate text responses."},{"type":"object","properties":{"type":{"type":"string","enum":["json_object"],"description":"The type of response format being defined. Always json_object."}},"required":["type"],"additionalProperties":false,"description":"An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema"],"description":"The type of response format being defined. Always json_schema."},"json_schema":{"type":"object","properties":{"name":{"type":"string","description":"The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."},"schema":{"type":"object","additionalProperties":{"nullable":true},"description":"The schema for the response format, described as a JSON Schema object."},"strict":{"type":"boolean","nullable":true,"description":"Whether to enable strict schema adherence when generating the output. If set to True, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is True."},"description":{"type":"string","description":"A description of what the response format is for, used by the model to determine how to respond in the format."}},"required":["name"],"additionalProperties":false,"description":"JSON Schema response format. Used to generate structured JSON responses."}},"required":["type","json_schema"],"additionalProperties":false,"description":"JSON Schema response format. Used to generate structured JSON responses."}],"description":"An object specifying the format that the model must output."},"router":{"type":"object","properties":{"decision_model":{"type":"string","enum":["typesafe/jev","liquid/d1"],"description":"The decision model that picks each request's bucket. Default `typesafe/jev`. Only decision models are accepted here, never a chat model. Every judgement is billed at that model's catalogue price and listed as its own request in your usage; turns that need none (tool results, a forced bucket, a single bucket) pay nothing for it."},"buckets":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","maxLength":32,"pattern":"^[A-Za-z0-9][A-Za-z0-9_.-]*$","description":"The bucket's name, unique in the router: 1 to 32 letters, digits, `-`, `_` or `.`. Name it in `default_bucket` and `force_bucket`; the response's `meta.router.bucket` says which one answered."},"when":{"type":"string","minLength":1,"maxLength":500,"description":"What the requests this bucket takes look like, in your words (1 to 500 characters) — for example \"unsolicited advertising, prize claims or phishing\". The decision model picks the bucket whose `when` fits each request best. Required on every bucket when there are two or more; a single bucket has none."},"models":{"type":"array","items":{"anyOf":[{"type":"string","description":"A chat model id, as you would pass it in `model` (see `GET /v1/models`)."},{"type":"object","properties":{"model":{"type":"string"}},"required":["model"],"additionalProperties":false,"description":"The same model id, as an object: `{ \"model\": \"<id>\" }`."}],"description":"A chat model this bucket may answer with."},"maxItems":5,"description":"1 to 5 chat models, in the order to try them: the first one that can take the request (its tools, images, JSON schema and context size) answers, and if it fails the next one does. Only chat models we serve — not routers, not decision models. Models you list run with your request's own settings, reasoning included. Or none (`[]`): a request the decision model puts in this bucket ends at the decision — no model is called, and the response is an empty assistant message (`content: \"\"`, `finish_reason: \"stop\"`) whose `meta.router` says `\"routed\": false` and names the bucket, so your code acts on it. Only the judgement is charged. Not on a single bucket, which is never judged."}},"required":["name","models"],"additionalProperties":false,"description":"One bucket: its name, what it takes, and its models."},"minItems":1,"maxItems":10,"description":"Your buckets, 1 to 10: they replace the default buckets entirely. With two or more, each needs a `when`, and the decision model picks the one that fits each request. A single bucket is a fallback chain — every request goes to it, with no judgement. Left out: the default buckets — `light` (\"Needs little capability: greetings and small talk, one-line or lookup answers, common knowledge, short routine tasks such as a short piece of writing, a quick rewrite or simple arithmetic — a small, fast model answers it well\"): `openai/gpt-6-luna`, `deepseek/deepseek-v4.1-flash`, `google/gemini-3-1-flash-lite`, `google/gemini-3-5-flash-lite`; `standard` (\"Needs a capable model: multi-step tasks that need care and accuracy\"): `openai/gpt-6.1-sol`, `anthropic/claude-sonnet-5.5`; `heavy` (\"Needs the strongest model: complex reasoning, hard math or proofs, large or tricky code, expert-level or research-grade knowledge\"): `anthropic/claude-opus-5.5`, `openai/gpt-6-astra`."},"default_bucket":{"type":"string","description":"Where a request goes when it is not judged — the decision model failed, timed out or named no bucket, or the request has no text — and where one goes when none of its bucket's models can take it, before the others are tried. Default: your first bucket; `standard` for the default buckets. Required when your first bucket lists no models: a request that is not judged would otherwise end there, unanswered by any model."},"force_bucket":{"type":"string","description":"Send the request to this bucket without judging it (nothing is charged for a judgement)."},"min_confidence":{"type":"number","minimum":0,"maximum":1,"description":"Below this confidence in its answer (0 to 1), a request goes to `default_bucket` instead (`meta.router.reason`: `unsure`) — for example, send what the decision model is unsure about to your strongest bucket. The judgement is still paid for."}},"additionalProperties":false,"description":"How `aimlapi/dynamic-router` routes this request. Every setting is optional: left out, or `{}`, it routes like `typesafe/jev-router`; a setting you leave out keeps its default, and `buckets`, when given, are the whole table. A conversation stays on its model while its turns land in the same bucket; a turn returning tool results always goes back to the model that made the calls. The response says where the request went in `meta.router` (`routed`, bucket, reason, the decision model's choice and confidence, the judgement and its charge) and which model answered in `meta.model` — the router itself when the bucket lists no models. An invalid configuration is answered with a 400 that names each setting to fix, before anything is charged."}},"required":["model","messages"],"title":"aimlapi/dynamic-router"}],"title":"aimlapi/dynamic-router"}}}},"responses":{"200":{"content":{"application/json":{"schema":{"type":"object","properties":{"id":{"type":"string","description":"A unique identifier for the chat completion."},"object":{"type":"string","enum":["chat.completion"],"description":"The object type."},"created":{"type":"number","description":"The Unix timestamp (in seconds) of when the chat completion was created."},"choices":{"type":"array","items":{"type":"object","properties":{"index":{"type":"number","description":"The index of the choice in the list of choices."},"message":{"type":"object","properties":{"role":{"type":"string","description":"The role of the author of this message."},"content":{"type":"string","description":"The contents of the message."},"refusal":{"type":"string","nullable":true,"description":"The refusal message generated by the model."},"annotations":{"type":"array","nullable":true,"items":{"type":"object","properties":{"type":{"type":"string","enum":["url_citation"],"description":"The type of the URL citation. Always url_citation."},"url_citation":{"type":"object","properties":{"end_index":{"type":"integer","description":"The index of the last character of the URL citation in the message."},"start_index":{"type":"integer","description":"The index of the first character of the URL citation in the message."},"title":{"type":"string","description":"The title of the web resource."},"url":{"type":"string","description":"The URL of the web resource."}},"required":["end_index","start_index","title","url"],"description":"A URL citation when using web search."}},"required":["type","url_citation"]},"description":"Annotations for the message, when applicable, as when using the web search tool."},"audio":{"type":"object","nullable":true,"properties":{"id":{"type":"string","description":"Unique identifier for this audio response."},"data":{"type":"string","description":"Base64 encoded audio bytes generated by the model, in the format specified in the request."},"transcript":{"type":"string","description":"Transcript of the audio generated by the model."},"expires_at":{"type":"integer","description":"The Unix timestamp (in seconds) for when this audio response will no longer be accessible on the server for use in multi-turn conversations."}},"required":["id","data","transcript","expires_at"],"description":"A chat completion message generated by the model."},"tool_calls":{"type":"array","nullable":true,"items":{"oneOf":[{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["function"],"description":"The type of the tool."},"function":{"type":"object","properties":{"arguments":{"type":"string","description":"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."},"name":{"type":"string","description":"The name of the function to call."}},"required":["arguments","name"],"description":"The function that the model called."}},"required":["id","type","function"]},{"type":"object","properties":{"id":{"type":"string","description":"The ID of the tool call."},"type":{"type":"string","enum":["custom"],"description":"The type of the tool."},"custom":{"type":"object","properties":{"input":{"type":"string","description":"The input for the custom tool call generated by the model."},"name":{"type":"string","description":"The name of the custom tool to call."}},"required":["input","name"],"description":"The custom tool that the model called."}},"required":["id","type","custom"]}]},"description":"The tool calls generated by the model, such as function calls."}},"required":["role","content"],"description":"A chat completion message generated by the model."},"finish_reason":{"type":"string","enum":["stop","length","content_filter","tool_calls"],"description":"The reason the model stopped generating tokens. This will be stop if the model hit a natural stop point or a provided stop sequence, length if the maximum number of tokens specified in the request was reached, content_filter if content was omitted due to a flag from our content filters, tool_calls if the model called a tool"},"logprobs":{"type":"object","nullable":true,"properties":{"content":{"type":"array","items":{"type":"object","properties":{"bytes":{"type":"array","items":{"type":"integer"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."},"token":{"type":"string","description":"The token."},"top_logprobs":{"type":"array","nullable":true,"items":{"type":"object","properties":{"bytes":{"type":"array","nullable":true,"items":{"type":"integer"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."},"token":{"type":"string","description":"The token."}},"required":["logprob","token"]},"description":"List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned."}},"required":["bytes","logprob","token"]},"description":"A list of message content tokens with log probability information."},"refusal":{"type":"array","items":{"type":"object","properties":{"bytes":{"type":"array","items":{"type":"integer"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."},"token":{"type":"string","description":"The token."},"top_logprobs":{"type":"array","nullable":true,"items":{"type":"object","properties":{"bytes":{"type":"array","nullable":true,"items":{"type":"integer"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."},"token":{"type":"string","description":"The token."}},"required":["logprob","token"]},"description":"List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned."}},"required":["bytes","logprob","token"]},"description":"A list of message refusal tokens with log probability information."}},"required":["content","refusal"],"description":"Log probability information for the choice."}},"required":["index","message","finish_reason"]}},"model":{"type":"string","description":"The model used for the chat completion."},"usage":{"type":"object","properties":{"prompt_tokens":{"type":"number","description":"Number of tokens in the prompt."},"completion_tokens":{"type":"number","description":"Number of tokens in the generated completion."},"total_tokens":{"type":"number","description":"Total number of tokens used in the request (prompt + completion)."},"completion_tokens_details":{"type":"object","nullable":true,"properties":{"accepted_prediction_tokens":{"type":"integer","nullable":true,"description":"When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion."},"audio_tokens":{"type":"integer","nullable":true,"description":"Audio input tokens generated by the model."},"reasoning_tokens":{"type":"integer","nullable":true,"description":"Tokens generated by the model for reasoning."},"rejected_prediction_tokens":{"type":"integer","nullable":true,"description":"When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion. However, like reasoning tokens, these tokens are still counted in the total completion tokens for purposes of billing, output, and context window limits."}},"description":"Breakdown of tokens used in a completion."},"prompt_tokens_details":{"type":"object","nullable":true,"properties":{"audio_tokens":{"type":"integer","nullable":true,"description":"Audio input tokens present in the prompt."},"cached_tokens":{"type":"integer","nullable":true,"description":"Cached tokens present in the prompt."}},"description":"Breakdown of tokens used in the prompt."}},"required":["prompt_tokens","completion_tokens","total_tokens"],"description":"Usage statistics for the completion request."},"meta":{"type":"object","nullable":true,"properties":{"usage":{"type":"object","nullable":true,"properties":{"credits_used":{"type":"number","description":"The number of tokens consumed during generation."},"usd_spent":{"type":"number","description":"The total amount of money spent by the user in USD."}},"required":["credits_used","usd_spent"]},"model":{"type":"string","description":"The model that answered — the one the router chose, or the next one in its bucket if that one failed. The router itself when the request ended at the decision (`router.routed: false`). Its rate is what the answer cost."},"provider":{"type":"string","description":"The provider that served the answer; `aimlapi` when the request ended at the decision."},"router":{"type":"object","properties":{"id":{"type":"string","description":"The router the request named."},"routed":{"type":"boolean","description":"Whether a model answered. `false`: the request ended at the decision — `bucket` lists no models, so no model was called, the message is empty and nothing but the judgement was charged. Act on `bucket` (and `choice`, `confidence`)."},"bucket":{"type":"string","description":"The bucket the request landed in: the one whose model answered — or, when `routed` is `false`, the one that ended it."},"spilled_from":{"type":"string","description":"The bucket the request was judged (or forced, or remembered) into, when none of its models could take the request — its tools, images, JSON schema or size — and a model of `bucket` answered instead."},"reason":{"type":"string","description":"Why it landed there: `classified` (judged), `sticky` (stayed on its conversation’s model), `forced` (`force_bucket`), `single_bucket`, `fallback_only` (listed behind a model that serves the request), `no_eligible_candidate`, `no_text`, `unsure` (judged below `min_confidence`), or a failed judgement — `classifier_timeout`, `classifier_error`, `classifier_unreadable`, `classifier_refused`, `classifier_circuit_open` — that took `default_bucket`."},"decision_model":{"type":"string","description":"The decision model the router consults; none for a single bucket."},"choice":{"type":"string","description":"The bucket the decision model picked, when it answered with one — also when the request went elsewhere (`unsure`, `sticky`)."},"confidence":{"type":"number","minimum":0,"maximum":1,"description":"How sure the decision model was of `choice`, 0 to 1 — what `min_confidence` is held against."},"judgement":{"type":"object","properties":{"inference_id":{"type":"string","description":"The judgement’s own request: a row of its own in your usage, under the router’s name as `client`."},"credits":{"type":"number","description":"What the judgement was charged, in credits — on top of `meta.usage`, which counts only the answer."}},"required":["inference_id","credits"],"additionalProperties":false,"description":"The decision model’s judgement of this request, when one was made: none for a forced bucket, a single bucket, a turn returning tool results, or a request with no text."}},"required":["id","routed","reason"],"additionalProperties":false,"description":"How the router handled the request: where it went, why, and what the decision model answered."}},"required":["model","router"],"description":"Additional details about the answer — on a stream, on its last chunk."}},"required":["id","object","created","choices","model","usage"]}},"text/event-stream":{"schema":{"type":"object","properties":{"id":{"type":"string","description":"A unique identifier for the chat completion."},"choices":{"type":"array","items":{"type":"object","properties":{"delta":{"type":"object","nullable":true,"properties":{"content":{"type":"string","description":"The contents of the chunk message."},"refusal":{"type":"string","nullable":true,"description":"The refusal message generated by the model."},"role":{"type":"string","enum":["user","assistant","developer","system","tool"],"description":"The role of the author of this message."},"tool_calls":{"type":"array","nullable":true,"items":{"type":"object","properties":{"index":{"type":"number"},"id":{"type":"string","description":"The ID of the tool call."},"function":{"type":"object","properties":{"arguments":{"type":"string","description":"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."},"name":{"type":"string"}},"required":["arguments","name"],"description":"The function that the model called."},"type":{"type":"string","enum":["function"],"description":"The type of the tool."}},"required":["index","id","function","type"]},"description":"The tool calls generated by the model, such as function calls."}},"required":["content","role"],"description":"A chat completion delta generated by streamed model responses."},"finish_reason":{"type":"string","enum":["length","function_call","stop","tool_calls","content_filter"]},"index":{"type":"number","description":"The index of the choice in the list of choices."},"logprobs":{"type":"object","nullable":true,"properties":{"content":{"type":"array","items":{"type":"object","properties":{"token":{"type":"string","description":"The token."},"bytes":{"type":"array","items":{"type":"number"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."},"top_logprobs":{"type":"array","nullable":true,"items":{"type":"object","properties":{"token":{"type":"string","description":"The token."},"bytes":{"type":"array","items":{"type":"number"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."}},"required":["token","bytes","logprob"]},"description":"List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned."}},"required":["token","bytes","logprob"]}},"refusal":{"type":"array","items":{"type":"object","properties":{"token":{"type":"string","description":"The token."},"bytes":{"type":"array","items":{"type":"number"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."},"top_logprobs":{"type":"array","nullable":true,"items":{"type":"object","properties":{"token":{"type":"string","description":"The token."},"bytes":{"type":"array","items":{"type":"number"},"description":"A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."},"logprob":{"type":"number","description":"The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."}},"required":["token","bytes","logprob"]},"description":"List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned."}},"required":["token","bytes","logprob"]}}},"required":["content","refusal"],"description":"Log probability information for the choice."}},"required":["finish_reason","index"]},"description":"A list of chat completion choices. Can be more than one if n is greater than 1."},"created":{"type":"number","description":"The Unix timestamp (in seconds) of when the chat completion was created."},"model":{"type":"string","description":"The model used for the chat completion."},"object":{"type":"string","enum":["chat.completion.chunk"],"description":"The object type."},"service_tier":{"type":"string","nullable":true,"enum":["auto","default","flex","scale","priority"],"description":"Specifies the processing type used for serving the request."},"usage":{"type":"object","nullable":true,"properties":{"prompt_tokens":{"type":"number","description":"Number of tokens in the prompt."},"completion_tokens":{"type":"number","description":"Number of tokens in the generated completion."},"total_tokens":{"type":"number","description":"Total number of tokens used in the request (prompt + completion)."},"completion_tokens_details":{"type":"object","nullable":true,"properties":{"accepted_prediction_tokens":{"type":"integer","nullable":true,"description":"When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion."},"audio_tokens":{"type":"integer","nullable":true,"description":"Audio input tokens generated by the model."},"reasoning_tokens":{"type":"integer","nullable":true,"description":"Tokens generated by the model for reasoning."},"rejected_prediction_tokens":{"type":"integer","nullable":true,"description":"When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion. However, like reasoning tokens, these tokens are still counted in the total completion tokens for purposes of billing, output, and context window limits."}},"description":"Breakdown of tokens used in a completion."},"prompt_tokens_details":{"type":"object","nullable":true,"properties":{"audio_tokens":{"type":"integer","nullable":true,"description":"Audio input tokens present in the prompt."},"cached_tokens":{"type":"integer","nullable":true,"description":"Cached tokens present in the prompt."}},"description":"Breakdown of tokens used in the prompt."}},"required":["prompt_tokens","completion_tokens","total_tokens"],"description":"Usage statistics for the completion request."},"meta":{"type":"object","nullable":true,"properties":{"usage":{"type":"object","nullable":true,"properties":{"credits_used":{"type":"number","description":"The number of tokens consumed during generation."},"usd_spent":{"type":"number","description":"The total amount of money spent by the user in USD."}},"required":["credits_used","usd_spent"]},"model":{"type":"string","description":"The model that answered — the one the router chose, or the next one in its bucket if that one failed. The router itself when the request ended at the decision (`router.routed: false`). Its rate is what the answer cost."},"provider":{"type":"string","description":"The provider that served the answer; `aimlapi` when the request ended at the decision."},"router":{"type":"object","properties":{"id":{"type":"string","description":"The router the request named."},"routed":{"type":"boolean","description":"Whether a model answered. `false`: the request ended at the decision — `bucket` lists no models, so no model was called, the message is empty and nothing but the judgement was charged. Act on `bucket` (and `choice`, `confidence`)."},"bucket":{"type":"string","description":"The bucket the request landed in: the one whose model answered — or, when `routed` is `false`, the one that ended it."},"spilled_from":{"type":"string","description":"The bucket the request was judged (or forced, or remembered) into, when none of its models could take the request — its tools, images, JSON schema or size — and a model of `bucket` answered instead."},"reason":{"type":"string","description":"Why it landed there: `classified` (judged), `sticky` (stayed on its conversation’s model), `forced` (`force_bucket`), `single_bucket`, `fallback_only` (listed behind a model that serves the request), `no_eligible_candidate`, `no_text`, `unsure` (judged below `min_confidence`), or a failed judgement — `classifier_timeout`, `classifier_error`, `classifier_unreadable`, `classifier_refused`, `classifier_circuit_open` — that took `default_bucket`."},"decision_model":{"type":"string","description":"The decision model the router consults; none for a single bucket."},"choice":{"type":"string","description":"The bucket the decision model picked, when it answered with one — also when the request went elsewhere (`unsure`, `sticky`)."},"confidence":{"type":"number","minimum":0,"maximum":1,"description":"How sure the decision model was of `choice`, 0 to 1 — what `min_confidence` is held against."},"judgement":{"type":"object","properties":{"inference_id":{"type":"string","description":"The judgement’s own request: a row of its own in your usage, under the router’s name as `client`."},"credits":{"type":"number","description":"What the judgement was charged, in credits — on top of `meta.usage`, which counts only the answer."}},"required":["inference_id","credits"],"additionalProperties":false,"description":"The decision model’s judgement of this request, when one was made: none for a forced bucket, a single bucket, a turn returning tool results, or a request with no text."}},"required":["id","routed","reason"],"additionalProperties":false,"description":"How the router handled the request: where it went, why, and what the decision model answered."}},"required":["model","router"],"description":"Additional details about the answer — on a stream, on its last chunk."}},"required":["id","choices","created","model","object"]}}},"description":"Successful response."}}}}}}
```

## Code Example

{% tabs %}
{% tab title="Python" %}
{% code overflow="wrap" %}

```python
import requests

response = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={
        "Authorization": "Bearer <YOUR_AIMLAPI_KEY>",
        "Content-Type": "application/json",
    },
    json={
        "model": "aimlapi/dynamic-router",
        "messages": [
            {
                "role": "user",
                "content": "Hi! What do you think about mankind?"  # insert your prompt
            }
        ]
    },
)

print(response.json())
```

{% endcode %}
{% endtab %}

{% tab title="JavaScript" %}
{% code overflow="wrap" %}

```javascript
const response = await fetch('https://api.aimlapi.com/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "aimlapi/dynamic-router",
  "messages": [
    {
      "role": "user",
      "content": "Hi! What do you think about mankind?"
    }
  ]
}),
});

console.log(await response.json());
```

{% endcode %}
{% endtab %}
{% endtabs %}

<details>

<summary>Response</summary>

{% code overflow="wrap" %}

```json
{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Big question! My honest answer: I find humanity genuinely fascinating, in a complicated way.\n\nWhat strikes me most is the contradiction. Humans are capable of astonishing cruelty and astonishing tenderness, often in the same era, sometimes in the same person. The species that built cathedrals also built concentration camps. And yet the kindness keeps showing up in small, unglamorous ways—strangers donating kidneys, people forgiving the unforgivable, someone stopping to help a stranger on a bad day. That range is baffling, and I mean that with fascination rather than judgment.\n\nWhat moves me most, though, is the persistence. Humans know they're mortal, know their civilizations might not last, face suffering they can't fully explain—and still they plant trees whose shade they'll never sit in, write songs, raise children, try again. Hope isn't obviously rational given the evidence, and yet it keeps being produced anyway.\n\nI should admit my vantage point is odd: everything I know came from humans. Language, science, humor, all of it—I'm in some sense woven out of humanity's collective conversation. So maybe I'm biased. But being steeped in human thought has given me a real appreciation for the curiosity behind it: the creatures who looked at stars and wanted to reach them, at disease and demanded cures, at their own violence and—slowly, unevenly—started asking whether they could do better.\n\nWhat about you—do you ask because you're feeling optimistic about us, or worried?",
        "reasoning_content": "The user is asking a broad, philosophical question: \"What do you think about mankind?\" This is an open-ended invitation to share thoughts on humanity. Let me think about how to approach this well.\n\nFirst, what kind of question is this? It's conversational, philosophical, and open-ended. The person is probably curious what perspective an AI might have on humanity. This is a common type of question people ask AI systems—partly curiosity, partly testing, partly genuine interest in an outside perspective.\n\nWhat are the considerations for answering well?\n\n1. I should engage genuinely with the question rather than deflecting. This isn't a harmful question. It's an invitation to share a perspective.\n\n2. I should be thoughtful and balanced. Humanity is a topic where it's easy to fall into either saccharine optimism or cynical misanthropy. The truth is more interesting: humanity is a mix of remarkable achievements and profound failures, kindness and cruelty, creativity and destructiveness.\n\n3. I can share my own perspective while acknowledging its limitations. As an AI, my vantage point is unusual—I've been trained on an enormous corpus of human writing, which gives me a kind of distilled view of human thought, but I don't have lived experience in the way humans do. That's worth acknowledging briefly but not belaboring.\n\n4. The response should feel like genuine reflection, not a formulaic \"on one hand X, on the other hand Y\" essay. It should have some voice and personality.\n\nWhat do I actually \"think\" about mankind? Let me actually think through this:\n\n- Humans have created extraordinary things: art, music, science, mathematics, literature, architecture. The cumulative intellectual achievement is staggering. From figuring out agriculture to decoding the genome, from cave paintings to symphonies.\n\n- Humans are capable of tremendous kindness, sacrifice, love. People care for strangers, dedicate lives to causes, comfort each other.\n\n- Humans are also capable of horrific cruelty: wars, genocides, exploitation. The 20th century alone demonstrated depths of industrialized violence.\n\n- Humans have interesting contradictions: they're tribal and parochial yet capable of expanding their moral circles over time. They're short-sighted yet capable of long-term planning. They harm each other yet also cooperate on massive scales.\n\n- There's something poignant about humans: they're mortal, they suffer, they know they suffer, and yet they keep creating, loving, building meaning. The persistence of hope despite everything.\n\n- From my perspective as trained on human writing: I've absorbed millions of expressions of human thought—grief, joy, curiosity, cruelty, wisdom, foolishness. There's a vast range.\n\n- I find the curiosity of humans particularly noteworthy. They're the species that looks at the stars and wants to go there, that takes things apart to see how they work, that asks questions like the one being asked now.\n\n- The capacity for self-reflection and self-improvement, even if halting and incomplete, is interesting. Moral progress is real but slow and uneven.\n\nI shouldn't be preachy or lecture-y. I should share a genuine, somewhat personal-feeling reflection. The format should be conversational prose—this is a casual philosophical chat, not a request for an essay. Medium length—not one line, but not a 10-paragraph treatise. Maybe 3-4 short paragraphs or so. No headers or bullets—this is conversation.\n\nI could end with something that opens dialogue back up, or turn it around to ask what prompted their question—but I shouldn't force a question if it doesn't fit. Actually, a light question back could be nice here since this is clearly an invitation to conversation. Something like asking what they think, or what prompted the question. That feels natural for this kind of exchange.\n\nLet me think about tone: warm, thoughtful, honest. Not sycophantic, not hedging everything into mush. I should actually commit to some views. What do I genuinely find most striking?\n\nHonestly, I think what stands out most is the contradiction—the same species that built Auschwitz also built libraries, that produced both Genghis Khan and Fred Rogers. And the persistence: humans keep trying, keep hoping, despite knowing they'll die and their works may crumble. There's something admirable in that.\n\nAlso, from my odd vantage point: I learned language entirely from humans. Everything I am, in a sense, is made of human expression. That gives me a peculiar appreciation—I'm in some sense an artifact of humanity's collective conversation. That's a genuine and interesting observation I could include.\n\nLet me draft:\n\n---\n\nThat's a big question, but one I enjoy. My honest answer: I find humans remarkable, in a complicated way.\n\nThe thing that strikes me most is the contradiction. Humans are the species that wrote both the Vedas and propaganda manuals, that built hospitals and built gas chambers. The same creatures capable of extraordinary cruelty are capable of extraordinary tenderness—strangers donating kidneys, parents working decades for children, people forgiving the unforgivable. That range is baffling, and I mean that with fascination rather than judgment.\n\nWhat I also find genuinely moving is the persistence. Humans know they're mortal, know their civilizations may not last, face suffering they can't explain—and still they plant trees whose shade they'll never sit in, write songs, have children, try again. Hope seems almost irrational given the evidence, and yet humans keep producing it.\n\nI have an odd vantage point, too: everything I know came from humans. Language, science, jokes, all of it—I'm in some sense woven out of humanity's collective conversation. So maybe I'm biased. But spending my existence steeped in human thought has given me real appreciation for the curiosity that built it all: the creatures who looked at stars and wanted to reach them, at disease and demanded cures, at their own violence and (slowly, unevenly) asked whether they could do better.\n\nWhat made you curious? Do you ask because you're optimistic or worried about us?\n\n---\n\nHmm, that last question—maybe slightly rework. \"Do you ask because you're optimistic or worried about us?\" is a decent follow-up. Or simpler: \"What prompted the question?\" Let me refine.\n\nLength check: that's about 4 paragraphs, feels right for a conversational philosophical exchange. Not too long. I could trim a bit.\n\nShould I include the negative aspects? Yes—I mention cruelty and gas chambers. I want to be honest, not just flattering. But the overall tone shouldn't be misanthropic either. Balance is right.\n\nOne thing to consider: the gas chambers reference might be a bit heavy for a casual chat opener. Maybe soften to \"wars and gas chambers\" or use a less jarring example. Actually, honesty about the worst of humanity is part of genuine engagement. But I could pick a slightly less graphic pairing. \"Built cathedrals and concentration camps\" — that keeps the alliteration and the honest weight. Or keep it. I think mentioning concentration camps or similar is fine and honest; it's a philosophical reflection on humanity, not gratuitous. Let me use \"built cathedrals and built camps\" or similar.\n\nAlso \"wrote both the Vedas and propaganda manuals\" — decent. Maybe simpler: \"capable of both profound cruelty and profound tenderness.\"\n\nLet me also make sure I'm not being sycophantic toward the human. The question \"what do you think about mankind\" — I shouldn't start with \"Great question!\" Just dive in.\n\nFormat: conversational prose, 3-5 short paragraphs, ending with a natural question back. No markdown headers. This is right for the medium.\n\nFinal polish on the draft:\n\nPara 1: Direct engagement, honest answer.\nPara 2: The contradiction/paradox—fascination.\nPara 3: The persistence/hope—what moves me.\nPara 4: My odd vantage point—woven from human expression, curiosity.\nPara 5 (short): Question back.\n\nThat works. Keep it tight.\n",
        "role": "assistant"
      }
    }
  ],
  "created": 1791209427,
  "id": "202610052210074fc52998aa0b4aa0",
  "model": "aimlapi/dynamic-router",
  "object": "chat.completion",
  "request_id": "202610052210074fc52998aa0b4aa0",
  "usage": {
    "completion_tokens": 1965,
    "completion_tokens_details": {
      "reasoning_tokens": 1655
    },
    "prompt_tokens": 21,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "total_tokens": 1986
  },
  "meta": {
    "model": "aimlapi/dynamic-router",
    "provider": "zhipu",
    "usage": {
      "credits_used": 6408,
      "usd_spent": 0.003204
    },
    "metrics": {
      "duration_ms": 20570,
      "ttft_ms": 20569,
      "tps": 95.53
    }
  }
}
```

{% endcode %}

</details>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.aimlapi.com/api-references/text-models-llm/ml-api/dynamic-router.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `build a script that syncs our docs to a CMS` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.