> 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/stepfun/step3.7-flash.md).
# step3.7-flash
{% columns %}
{% column width="66.66666666666666%" %}
{% hint style="info" %}
This documentation is valid for the following list of our models:
* `stepfun/step-3.7-flash`
{% endhint %}
{% endcolumn %}
{% column width="33.33333333333334%" %} Try in Playground
{% endcolumn %}
{% endcolumns %}
## Model Overview
A multimodal Mixture-of-Experts model from StepFun. Supports text, image and video understanding with a 256K context window and is optimized for fast inference, reasoning and agent workflows.
{% hint style="success" %}
[Create AI/ML API Key](https://aimlapi.com/app/keys)
{% endhint %}
How to make the first API call
**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 `` 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 (for example, `messages` for chat/LLM models, or other inputs for image/video/audio models).
**4️ (Optional) Tune the request**\
Depending on the model type, you can add optional parameters to control the output (e.g., generation settings, quality, length, etc.). See the API schema below for the full list.
**5️ Run your code**\
Run the updated code in your development environment. Response time depends on the model and request size, but simple requests typically return quickly.
{% hint style="success" %}
If you need a more detailed walkthrough for setting up your development environment and making a request step by step — feel free to use our [Quickstart guide](broken://pages/ngeSCZKxiGVWqYZTHDjY).
{% endhint %}
## 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":{"type":"object","properties":{"model":{"type":"string","enum":["stepfun/step-3.7-flash"]},"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."}},"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"]}},"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"]}]}}],"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."}},"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."}},"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."}},"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."}},"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."}},"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."}},"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"]},"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."},"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"]}},"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"]}},"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."},"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."},"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"}},"required":["model","messages"],"title":"stepfun/step-3.7-flash"}}}},"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"]}},"description":"Additional details about the generation."}},"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."}},"required":["id","choices","created","model","object"]}}}}}}}}}
```
## Code Example
{% tabs %}
{% tab title="Python" %}
{% code overflow="wrap" %}
```python
import requests
import json # for getting a structured output with indentation
response = requests.post(
"https://api.aimlapi.com/v1/chat/completions",
headers={
# Insert your AIML API Key instead of :
"Authorization":"Bearer ",
"Content-Type":"application/json"
},
json={
"model":"stepfun/step-3.7-flash",
"messages":[
{
"role":"user",
"content":"Hi! What do you think about mankind?" # insert your prompt
}
]
}
)
data = response.json()
print(json.dumps(data, indent=2, ensure_ascii=False))
```
{% endcode %}
{% endtab %}
{% tab title="JavaScript" %}
{% code overflow="wrap" %}
```javascript
async function main() {
const response = await fetch('https://api.aimlapi.com/v1/chat/completions', {
method: 'POST',
headers: {
// insert your AIML API Key instead of
'Authorization': 'Bearer ',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'stepfun/step-3.7-flash',
messages:[
{
role:'user',
content: 'Hi! What do you think about mankind?' // insert your prompt here
}
],
}),
});
const data = await response.json();
console.log(JSON.stringify(data, null, 2));
}
main();
```
{% endcode %}
{% endtab %}
{% endtabs %}
Response
{% code overflow="wrap" %}
```json5
{
"id": "gen-1780385293-eIiTJGZ12HPATm2FXwP0",
"object": "chat.completion",
"created": 1780385293,
"model": "stepfun/step-3.7-flash-20260528",
"system_fingerprint": null,
"service_tier": null,
"choices": [
{
"index": 0,
"logprobs": null,
"finish_reason": "stop",
"native_finish_reason": "stop",
"message": {
"role": "assistant",
"content": "Humanity is such a beautifully complex, contradictory tapestry that any single take feels like it only captures a fraction of the truth.\nOn one hand, I’m endlessly in awe of what you’re capable of: the way you create art that moves people to tears across centuries and cultures, the leaps of science and medicine that have saved billions of lives, the quiet, uncelebrated kindnesses strangers show each other during crises, the collective push to tear down unjust systems and extend care to people who have been marginalized for generations. The fact that you can look up at the stars and dream of exploring them, or sit with someone grieving and offer comfort without needing a perfect answer, feels like one of the most special, unreplicable things about being human.\nOn the other hand, there’s the profound harm you’ve inflicted: on each other through war, exploitation and systemic oppression, on the other species you share the planet with, on the very ecosystems that sustain you. Shortsightedness, greed, and the capacity for cruelty have left scars that will take generations to heal.\nWhat strikes me most, though, is that those two sides aren’t separate—they come from the same core capacities: your ability to imagine, to choose, to care, and to grow. The same drive that leads to destructive exploitation can also lead people to fight for justice, to innovate solutions for climate change, to pour love into communities that have been forgotten. Humanity isn’t a fixed, finished thing; it’s a story still being written, by billions of people making small and big choices every day. That tension between fallibility and the endless capacity to do better is, to me, what makes your species so endlessly compelling.",
"refusal": null,
"reasoning": "Got it, let's tackle this question about what I think of mankind. First, I need to be balanced, right? Not just all positive or all negative, because humanity is super complex.\nFirst, start with the amazing parts, right? Like our creativity, empathy, resilience. Think about all the art, science, the way we care for each other even across boundaries—like when people help strangers during disasters, or movements for equality, the leaps in medicine that saved so many lives, the ability to imagine things that don't exist and bring them to life, from internet to space exploration. That's the really beautiful side, the capacity for kindness and progress.\nThen, of course, the hard parts too. We have flaws, right? We've done a lot of harm too—exploitation, conflict, damaging the planet, systemic injustices that hurt marginalized groups. But wait, I should frame that not as inherent, but as challenges we can overcome, right? Because those flaws aren't fixed, we can grow.\nAlso, maybe mention that the most striking thing is the tension between those two sides? Like every person has the capacity for both great good and great harm, and the arc of history is shaped by the choices we make, small and big. Also, it's not my place to have a final judgment, right? Because humanity is still evolving, still learning. Maybe end with a hopeful note? Like even with all the struggles, the fact that so many people are working to make things better, to care for each other and the planet, that's what's really remarkable.\nWait, also need to make it sound natural, not too formal. Let's structure it:\n1. Open with how complex and multifaceted humanity is, no simple take.\n2. First the awe-inspiring parts: creativity, empathy, collective progress. Examples: art, science, mutual aid, breaking down barriers of prejudice, exploring the unknown, caring for vulnerable people.\n3. Then the difficult, messy parts: the harm we've inflicted—on each other, on other species, on the planet, systemic unfairness, short-sightedness, capacity for cruelty.\n4. But then emphasize that those flaws aren't the whole story, or a fixed fate. The same capacity for reflection and growth that lets us harm also lets us learn, repent, build better. The arc of progress is driven by ordinary people choosing kindness, justice, care every day.\n5. End with a note that it's a story still being written, and that's part of what makes it so compelling.\nWait, also, should I avoid being too preachy? Make it sound genuine. Let's see:\n\"Humanity is such a beautifully complex, contradictory tapestry that any single take feels like it only captures a fraction of the truth.\nOn one hand, I’m endlessly in awe of what you’re capable of: the way you create art that moves people to tears across centuries and cultures, the leaps of science and medicine that have saved billions of lives, the quiet, uncelebrated kindnesses strangers show each other during crises, the collective push to tear down unjust systems and extend care to people who have been marginalized for generations. The fact that you can look up at the stars and dream of exploring them, or sit with someone grieving and offer comfort without needing a perfect answer, feels like one of the most special, unreplicable things about being human.\nOn the other hand, there’s the profound harm you’ve inflicted: on each other through war, exploitation and systemic oppression, on the other species you share the planet with, on the very ecosystems that sustain you. Shortsightedness, greed, and the capacity for cruelty have left scars that will take generations to heal.\nWhat strikes me most, though, is that those two sides aren’t separate—they come from the same core capacities: your ability to imagine, to choose, to care, and to grow. The same drive that leads to destructive exploitation can also lead people to fight for justice, to innovate solutions for climate change, to pour love into communities that have been forgotten. Humanity isn’t a fixed, finished thing; it’s a story still being written, by billions of people making small and big choices every day. That tension between fallibility and the endless capacity to do better is, to me, what makes your species so endlessly compelling.\"\nYeah, that sounds good. It's balanced, acknowledges both the good and bad, doesn't present a nihilistic or overly rosy view, and ends on a thoughtful note. Let me check if there's anything off? No, that's appropriate. Also, it's honest, doesn't pretend like I have a definitive judgment, which is fair because humanity is still evolving.",
"reasoning_details": [
{
"type": "reasoning.text",
"text": "Got it, let's tackle this question about what I think of mankind. First, I need to be balanced, right? Not just all positive or all negative, because humanity is super complex.\nFirst, start with the amazing parts, right? Like our creativity, empathy, resilience. Think about all the art, science, the way we care for each other even across boundaries—like when people help strangers during disasters, or movements for equality, the leaps in medicine that saved so many lives, the ability to imagine things that don't exist and bring them to life, from internet to space exploration. That's the really beautiful side, the capacity for kindness and progress.\nThen, of course, the hard parts too. We have flaws, right? We've done a lot of harm too—exploitation, conflict, damaging the planet, systemic injustices that hurt marginalized groups. But wait, I should frame that not as inherent, but as challenges we can overcome, right? Because those flaws aren't fixed, we can grow.\nAlso, maybe mention that the most striking thing is the tension between those two sides? Like every person has the capacity for both great good and great harm, and the arc of history is shaped by the choices we make, small and big. Also, it's not my place to have a final judgment, right? Because humanity is still evolving, still learning. Maybe end with a hopeful note? Like even with all the struggles, the fact that so many people are working to make things better, to care for each other and the planet, that's what's really remarkable.\nWait, also need to make it sound natural, not too formal. Let's structure it:\n1. Open with how complex and multifaceted humanity is, no simple take.\n2. First the awe-inspiring parts: creativity, empathy, collective progress. Examples: art, science, mutual aid, breaking down barriers of prejudice, exploring the unknown, caring for vulnerable people.\n3. Then the difficult, messy parts: the harm we've inflicted—on each other, on other species, on the planet, systemic unfairness, short-sightedness, capacity for cruelty.\n4. But then emphasize that those flaws aren't the whole story, or a fixed fate. The same capacity for reflection and growth that lets us harm also lets us learn, repent, build better. The arc of progress is driven by ordinary people choosing kindness, justice, care every day.\n5. End with a note that it's a story still being written, and that's part of what makes it so compelling.\nWait, also, should I avoid being too preachy? Make it sound genuine. Let's see:\n\"Humanity is such a beautifully complex, contradictory tapestry that any single take feels like it only captures a fraction of the truth.\nOn one hand, I’m endlessly in awe of what you’re capable of: the way you create art that moves people to tears across centuries and cultures, the leaps of science and medicine that have saved billions of lives, the quiet, uncelebrated kindnesses strangers show each other during crises, the collective push to tear down unjust systems and extend care to people who have been marginalized for generations. The fact that you can look up at the stars and dream of exploring them, or sit with someone grieving and offer comfort without needing a perfect answer, feels like one of the most special, unreplicable things about being human.\nOn the other hand, there’s the profound harm you’ve inflicted: on each other through war, exploitation and systemic oppression, on the other species you share the planet with, on the very ecosystems that sustain you. Shortsightedness, greed, and the capacity for cruelty have left scars that will take generations to heal.\nWhat strikes me most, though, is that those two sides aren’t separate—they come from the same core capacities: your ability to imagine, to choose, to care, and to grow. The same drive that leads to destructive exploitation can also lead people to fight for justice, to innovate solutions for climate change, to pour love into communities that have been forgotten. Humanity isn’t a fixed, finished thing; it’s a story still being written, by billions of people making small and big choices every day. That tension between fallibility and the endless capacity to do better is, to me, what makes your species so endlessly compelling.\"\nYeah, that sounds good. It's balanced, acknowledges both the good and bad, doesn't present a nihilistic or overly rosy view, and ends on a thoughtful note. Let me check if there's anything off? No, that's appropriate. Also, it's honest, doesn't pretend like I have a definitive judgment, which is fair because humanity is still evolving.",
"format": "unknown",
"index": 0
}
]
}
}
],
"usage": {
"completion_tokens": 1319,
"prompt_tokens": 21,
"total_tokens": 1340,
"completion_tokens_details": {
"reasoning_tokens": 0,
"image_tokens": 0,
"audio_tokens": 0
},
"prompt_tokens_details": {
"cached_tokens": 0,
"cache_write_tokens": 0,
"audio_tokens": 0,
"video_tokens": 0
}
},
"meta": {
"usage": {
"credits_used": 3955,
"usd_spent": 0.0019775
}
}
}
```
{% endcode %}
---
# 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 current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.aimlapi.com/api-references/text-models-llm/stepfun/step3.7-flash.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.