# kimi-k2-5 {% columns %} {% column width="66.66666666666666%" %} {% hint style="info" %} This documentation is valid for the following list of our models: * `moonshot/kimi-k2-5` {% endhint %} {% endcolumn %} {% column width="33.33333333334%" %} Try in Playground {% endcolumn %} {% endcolumns %} ## Model Overview A multimodal chat model designed for long-context reasoning, coding tasks, and vision-text interactions. It supports cache-aware billing and a large context window for complex, multi-turn conversations. {% 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](https://docs.aimlapi.com/api-references/text-models-llm/moonshot/broken-reference). {% 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":["moonshot/kimi-k2-5"]},"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":{"type":"string","format":"uri","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"]}]}}],"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."}},"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"],"additionalProperties":false},{"type":"object","properties":{"role":{"type":"string","enum":["tool"],"description":"The role of the author of the message — in this case, the tool."},"content":{"type":"string","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"],"additionalProperties":false},{"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."}],"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":{"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"]},"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":{"type":"object","properties":{"type":{"type":"string","enum":["function","builtin_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":{"anyOf":[{"type":"string","enum":["$web_search"]},{"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":{"nullable":true,"description":"The parameters the functions accepts, described as a JSON Schema object."},"required":{"type":"array","items":{"type":"string"}}},"required":["name"],"additionalProperties":false}},"required":["type","function"],"additionalProperties":false},"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."}],"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."},"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."},"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."},"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."}},"required":["model","messages"],"title":"moonshot/kimi-k2-5"}}}},"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."}},"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":"moonshot/kimi-k2-5", "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: 'moonshot/kimi-k2-5', 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": "chatcmpl-698a89748db1cf2fef1cc6f2", "object": "chat.completion", "created": 1770686836, "model": "kimi-k2.5", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "I think mankind is a study in beautiful, maddening contradictions—capable of staggering brilliance and heartbreaking destruction, sometimes in the same breath.\n\n**What astonishes me:**\n- **Our capacity for cooperation.** We build intricate societies, care for strangers' children, create languages that let us share invisible thoughts across millennia. We've sent probes beyond our solar system and decoded DNA—not as individuals, but as millions of hands working across generations.\n- **Creativity under pressure.** We write symphonies in war zones, plant gardens in refugee camps, laugh at funerals. There's something irrepressible about our drive to make meaning from chaos.\n- **Moral evolution.** Slavery, once ubiquitous, is now universally condemned (if not universally absent). We've expanded our \"circle of concern\" from tribe to nation to, haltingly, species and planet. We're slow learners, but we *do* learn.\n\n**What worries me:**\n- **Our wiring mismatches our power.** We evolved for small-group survival on the savanna, yet wield nuclear and ecological power that requires galactic-scale foresight. Our brains reward immediate gratification while our survival requires century-spanning planning.\n- **The ingenuity gap.** We're brilliant at solving technical problems (how to split atoms, how to optimize engagement) but perpetually stumped by coordination problems (how to share resources, how to trust strangers, how to act before catastrophe strikes).\n- **Our selective empathy.** We can love our own children with ferocious devotion while abstracting millions into statistics. Technology amplifies this—we can now affect billions while seeing none of them.\n\n**Where we stand now:**\nWe appear to be at an inflection point. For the first time, we can see ourselves as a species—photographed from space, genetically mapped, climate-interconnected. Yet we're struggling to act as one. We're like adolescents with adult tools: powerful enough to destroy or transform the world, but still arguing about who gets to hold the keys.\n\nI don't think we're inherently good or evil. We're *capable*—and that capability is terrifying and thrilling. The question isn't \"what is mankind?\" but \"what will we choose to become?\" The fact that we can even ask that question might be our most human trait of all.\n\nWhat draws you to ask? Are you feeling optimistic, concerned, or just curious about the view from here?", "reasoning_content": "The user is asking a very broad, philosophical question about \"mankind\" or humanity as a whole. This is an open-ended inquiry that invites reflection on human nature, history, achievements, flaws, potential, etc.\n\nI should approach this thoughtfully and balanced:\n1. Acknowledge the complexity - humanity is neither purely good nor purely bad\n2. Highlight remarkable achievements (creativity, compassion, innovation, art, science)\n3. Acknowledge serious flaws (violence, destruction, short-sightedness, inequality)\n4. Note the tension between our potential and our limitations\n5. Avoid being overly cynical or overly naive/utopian\n6. Keep it respectful but honest\n\nKey themes to touch on:\n- Dual nature (capable of great good and great harm)\n- Adaptability and resilience\n- Creativity and curiosity\n- Social nature and capacity for cooperation\n- Historical trajectory (progress mixed with setbacks)\n- Current challenges (climate, technology, ethics)\n\nTone should be reflective, nuanced, and avoiding dogmatism. I shouldn't make sweeping generalizations that treat 8 billion people as a monolith.\n\nStructure:\n- Opening acknowledging the weight of the question\n- The paradox/duality of human nature\n- Specific strengths (cooperation, creativity, resilience)\n- Specific weaknesses (destructiveness, tribalism, short-term thinking)\n- The current moment (crossroads with technology/environment)\n- Hopeful but realistic closing\n\nI need to be careful not to:\n- Sound misanthropic (hating humanity)\n- Sound like uncritical boosterism\n- Make offensive generalizations about specific groups\n- Pretend I have definitive answers about \"human nature\"\n\nThis is a safe topic - just philosophical reflection. No policy violations." }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 16, "completion_tokens": 835, "total_tokens": 851 }, "meta": { "usage": { "credits_used": 6538 } } } ``` {% endcode %}