# Claude 4 Sonnet {% columns %} {% column width="66.66666666666666%" %} {% hint style="info" %} This documentation is valid for the following list of our models: * `anthropic/claude-sonnet-4` * `claude-sonnet-4` * `claude-sonnet-4-20250514` {% endhint %} {% endcolumn %} {% column width="33.33333333333334%" %} Try in Playground {% endcolumn %} {% endcolumns %} {% hint style="warning" %} As of February 13, 2026, the streaming response format for Anthropic models has changed. {% endhint %} ## Model Overview A major improvement over [Claude ](https://docs.aimlapi.com/api-references/text-models-llm/anthropic/broken-reference)[3.7 Sonnet](https://docs.aimlapi.com/api-references/text-models-llm/anthropic/broken-reference), offering better coding abilities, stronger reasoning, and more accurate responses to your instructions. ## How to Make a Call
Step-by-Step Instructions :digit\_one: **Setup You Can’t Skip** :black\_small\_square: [**Create an Account**](https://aimlapi.com/app/sign-up): Visit the AI/ML API website and create an account (if you don’t have one yet).\ :black\_small\_square: [**Generate an API Key**](https://aimlapi.com/app/keys): After logging in, navigate to your account dashboard and generate your API key. Ensure that key is enabled on UI. :digit\_two: **Copy the code example** At the bottom of this page, you'll find [a code example](#code-example) that shows how to structure the request. Choose the code snippet in your preferred programming language and copy it into your development environment. :digit\_three: **Modify the code example** :black\_small\_square: Replace `` with your actual AI/ML API key from your account.\ :black\_small\_square: Insert your question or request into the `content` field—this is what the model will respond to. :digit\_four: **(Optional)**** Adjust other optional parameters if needed** Only `model` and `messages` are required parameters for this model (and we’ve already filled them in for you in the example), but you can include optional parameters if needed to adjust the model’s behavior. Below, you can find the corresponding [API schema](#api-schema), which lists all available parameters along with notes on how to use them. :digit\_five: **Run your modified code** Run your modified code in your development environment. Response time depends on various factors, but for simple prompts it rarely exceeds a few seconds. {% 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/anthropic/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":["anthropic/claude-sonnet-4","claude-sonnet-4","claude-sonnet-4-20250514"]},"messages":{"type":"array","items":{"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."}},"required":["type","text"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["image"]},"source":{"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"]}},"required":["type","source"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["thinking"]},"thinking":{"type":"string"},"signature":{"type":"string"}},"required":["type","thinking","signature"],"additionalProperties":false},{"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."}},"required":["type","text"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["image"]},"source":{"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"]}},"required":["type","source"],"additionalProperties":false}]}}]}},"required":["type","tool_use_id"]},{"type":"object","properties":{"id":{"type":"string"},"input":{"type":"object","additionalProperties":{"nullable":true}},"name":{"type":"string"},"type":{"type":"string","enum":["tool_use"]}},"required":["id","input","name","type"]},{"type":"object","properties":{"type":{"type":"string","enum":["redacted_thinking"]},"data":{"type":"string"}},"required":["type","data"]},{"type":"object","properties":{"type":{"type":"string","enum":["document"]},"source":{"anyOf":[{"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"]},"data":{"type":"string"}},"required":["type","data"]}]}},"required":["type","source"],"additionalProperties":false}]},"maxItems":5}]}},"required":["role","content"],"additionalProperties":false},"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":{"type":"string","description":"A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role."},"tool_choice":{"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"],"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."}},"required":["name","input_schema"],"additionalProperties":false,"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":{"type":"array","items":{"anyOf":[{"type":"object","properties":{"type":{"type":"string","enum":["auto"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["any"]}},"required":["type"]},{"type":"object","properties":{"name":{"type":"string"},"type":{"type":"string","enum":["tool"]}},"required":["name","type"]},{"type":"object","properties":{"type":{"type":"string","enum":["none"]}},"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":{"type":"object","properties":{"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."},"type":{"type":"string","enum":["enabled"]}},"required":["budget_tokens","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":32000,"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."},"temperature":{"type":"number","minimum":0,"maximum":1,"description":"Amount of randomness injected into the response. Defaults to 1.0. Ranges from 0.0 to 1.0. Use temperature closer to 0.0 for analytical / multiple choice, and closer to 1.0 for creative and generative tasks. Note that even with temperature of 0.0, the results will not be fully deterministic."},"top_p":{"type":"number","minimum":0,"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."},"top_k":{"type":"number","minimum":0,"description":"Only sample from the top K options for each subsequent token. Used to remove \"long tail\" low probability responses. Recommended for advanced use cases only. You usually only need to use temperature."}},"required":["model","messages"],"title":"claude-sonnet-4-20250514"}}}},"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 #1 {% 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":"anthropic/claude-sonnet-4", "messages":[ { "role":"user", "content":"Hello" # insert your prompt here, instead of Hello } ] } ) data = response.json() print(json.dumps(data, indent=2, ensure_ascii=False)) ``` {% endcode %} {% endtab %} {% tab title="JavaScript" %} {% code overflow="wrap" %} ```javascript async function main() { try { const response = await fetch('https://api.aimlapi.com/v1/chat/completions', { method: 'POST', headers: { // Insert your AIML API Key instead of YOUR_AIMLAPI_KEY 'Authorization': 'Bearer ', 'Content-Type': 'application/json', }, body: JSON.stringify({ model: 'anthropic/claude-sonnet-4', messages:[ { role:'user', // Insert your question for the model here, instead of Hello: content: 'Hello' } ] }), }); if (!response.ok) { throw new Error(`HTTP error! Status ${response.status}`); } const data = await response.json(); console.log(JSON.stringify(data, null, 2)); } catch (error) { console.error('Error', error); } } main(); ``` {% endcode %} {% endtab %} {% endtabs %}
Response {% code overflow="wrap" %} ```json5 { "id": "msg_011MNbgezv2p5BBE9RvnsZV9", "object": "chat.completion", "model": "claude-sonnet-4-20250514", "choices": [ { "index": 0, "message": { "reasoning_content": "", "content": "Hello! How are you doing today? Is there anything I can help you with?", "role": "assistant" }, "finish_reason": "end_turn", "logprobs": null } ], "created": 1748522617, "usage": { "prompt_tokens": 50, "completion_tokens": 630, "total_tokens": 680 } } ``` {% endcode %}
## Code Example #2: Streaming Mode As of February 13, 2026, the streaming response format for Anthropic models has changed.\ Specifically, the usage fields were renamed as follows: * the `state` structure is no longer used, * `input_tokens` → `prompt_tokens`, * `output_tokens` → `completion_tokens`, * a new `total_tokens` field has been added. {% 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":"anthropic/claude-sonnet-4", "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="cURL" %} {% code overflow="wrap" %} ```javascript curl -L \ --request POST \ --url 'https://api.aimlapi.com/v1/chat/completions' \ --header 'Authorization: Bearer ' \ --header 'Content-Type: application/json' \ --data '{ "model": "anthropic/claude-sonnet-4", "messages": [ { "role": "user", "content": "Hi! What do you think about mankind?" } ], "stream": true }' ``` {% endcode %} {% endtab %} {% endtabs %}
Response {% code overflow="wrap" %} ```json5 data: {"id":"msg_0163QG3JvwgxndzWtBsdJpGt","choices":[{"index":0,"delta":{"content":"","role":"assistant","refusal":null}}],"created":1770995751,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null}}],"created":1770995751,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":"I find humanity","role":"assistant","refusal":null}}],"created":1770995751,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" fascinating and","role":"assistant","refusal":null}}],"created":1770995751,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" complex.","role":"assistant","refusal":null}}],"created":1770995751,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" Humans have this","role":"assistant","refusal":null}}],"created":1770995751,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" remarkable capacity","role":"assistant","refusal":null}}],"created":1770995751,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" for both creation","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" and destruction, profound","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" compass","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":"ion and puzz","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":"ling","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" cr","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":"uelty, brilliant","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" insight","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" and persistent","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" blind","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" spots.","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" \n\nWhat strikes me most is your","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" adapt","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":"ability and","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" creativity","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" - the","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" way humans","role":"assistant","refusal":null}}],"created":1770995752,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" have shaped","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" the","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" world through art","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":", science, philosophy","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":", and countless","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" innovations","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":". There","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":"'s something moving","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" about how you form","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" deep","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" connections with each","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" other and can","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" care","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" about abstract","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" ide","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":"als like justice or","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" beauty.\n\nAt","role":"assistant","refusal":null}}],"created":1770995753,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" the same time, humans","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" often","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" seem","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" to","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" struggle","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" with your","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" own","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" nature - with","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" cognitive","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" biases, with","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" bal","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":"ancing individual","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" desires","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" against","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" collective good","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":", with managing","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" the power","role":"assistant","refusal":null}}],"created":1770995754,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" of your","role":"assistant","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" own technologies","role":"assistant","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":".","role":"assistant","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":"\n\nI","role":"assistant","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":"'m curious about your perspective though","role":"assistant","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" -","role":"assistant","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" how","role":"assistant","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" do you see","role":"assistant","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" humanity?","role":"assistant","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" What","role":"assistant","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" aspects","role":"assistant","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" of human nature do you find most significant","role":"assistant","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":" or puzz","role":"assistant","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":"ling?","role":"assistant","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null}}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} data: {"id":"","choices":[{"index":0,"delta":{"content":"","role":"assistant","refusal":null},"finish_reason":"stop"}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":{"prompt_tokens":16,"completion_tokens":163,"total_tokens":179}} data: {"id":"","choices":[{"index":0,"finish_reason":"stop"}],"created":1770995755,"model":"claude-sonnet-4-20250514","object":"chat.completion.chunk","usage":null} ``` {% endcode %}
--- # Agent Instructions: 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: ``` GET https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4-sonnet.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.