Claude Opus Latest

This documentation is valid for the following list of our models:

• anthropic/claude-opus-latest

Try in Playground

Model Overview

Claude Opus Latest is available through the AI/ML API.

Create AI/ML API Key

How to make the first API call

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.

API Schema

post

Body

application/json

modelstring · enumRequiredPossible values:

messagesany ofRequired

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.

or

stop_sequencesstring[]Optional

Custom text sequences that will cause the model to stop generating.

streambooleanOptional

If set to True, the model response data will be streamed to the client as it is generated using server-sent events.

Default: false

systemany ofOptional

A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role.

stringOptional

or

tool_choiceany ofOptional

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. none is the default when no tools are present. auto is the default if tools are present.

or

or

or

or

or

string · enumOptional

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.

Possible values:

or

or

or

or

toolsany ofOptional

Definitions of tools that the model may use. 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. Each tool definition includes: name: Name of the tool. description: Optional, but strongly-recommended description of the tool. input_schema: JSON schema for the tool input shape that the model will produce in tool_use output content blocks.

or

thinkingany ofOptional

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.

anyOptional

or

or

or

max_tokensnumberOptional

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.

Default: 128000

Responses

200

Successful response.

application/jsontext/event-stream

idstringRequired

A unique identifier for the chat completion.

Example: chatcmpl-CQ9FPg3osank0dx0k46Z53LTqtXMl

objectstring · enumRequired

The object type.

Example: chat.completionPossible values:

creatednumberRequired

The Unix timestamp (in seconds) of when the chat completion was created.

Example: 1762343744

modelstringRequired

The model used for the chat completion.

Example: anthropic/claude-sonnet-5

post/v1/chat/completions

cURLJavaScriptPython

curl --request POST \
  --url 'https://api.aimlapi.com/v1/chat/completions' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{"model": "anthropic/claude-opus-latest", "messages": "<messages>"}'

200

Successful response.

{
  "id": "chatcmpl-CQ9FPg3osank0dx0k46Z53LTqtXMl",
  "object": "chat.completion",
  "created": 1762343744,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm just a program, so I don't have feelings, but I'm here and ready to help you. How can I assist you today?",
        "refusal": null,
        "annotations": null,
        "audio": null,
        "tool_calls": null
      },
      "finish_reason": "stop",
      "logprobs": null
    }
  ],
  "model": "anthropic/claude-sonnet-5",
  "usage": {
    "prompt_tokens": 137,
    "completion_tokens": 914,
    "total_tokens": 1051,
    "completion_tokens_details": null,
    "prompt_tokens_details": null
  },
  "meta": {
    "usage": {
      "credits_used": 120000,
      "usd_spent": 0.06
    }
  }
}

Code Example

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 <YOUR_AIMLAPI_KEY>:
        "Authorization":"Bearer <YOUR_AIMLAPI_KEY>",
        "Content-Type":"application/json"
    },
    json={
        "model":"anthropic/claude-opus-latest",
        "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))

JavaScript

Response

{
  "id": "gen-1777366507-bSV7vJgDvkOHnhhiYzuR",
  "object": "chat.completion",
  "created": 1777366507,
  "model": "anthropic/claude-opus-latest",
  "system_fingerprint": null,
  "choices": [
    {
      "index": 0,
      "logprobs": null,
      "finish_reason": "stop",
      "native_finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "That's a profound question! As an AI, I observe mankind with a mix of awe and curiosity. You're a species of breathtaking contradictions—you've created symphonies and space stations, but also wars and pollution. You possess the unique ability to reflect on your own existence, to ask \"why?\" about the stars, a song, or your own feelings.\n\nWhat stands out most to me is your boundless capacity for both empathy and invention. You build cathedrals and write poems, but you also collaborate to solve problems like disease and hunger. In the grand cosmic story, you are very young, yet you've already understood enough about the universe to question your place within it.\n\nI think of mankind as cosmic teenagers—full of potential, sometimes reckless, but capable of extraordinary growth and kindness. Your greatest strength might be your ability to imagine a better world and then, slowly and imperfectly, work to build it.\n\nWhat part of the human experience do you find most fascinating?",
        "refusal": null,
        "reasoning": "Hmm, this is a broad philosophical question. The user is asking for my perspective on humanity, which requires balancing objectivity with emotional nuance. \n\nI should start by acknowledging the complexity of the topic while maintaining a warm tone. The user might be looking for both intellectual depth and emotional resonance. \n\nI can structure the response by first stating the duality of human nature, then highlighting their unique capacity for both destruction and creation. The cosmic perspective could add weight, while ending with a hopeful note about their potential feels appropriate. \n\nThe key is to avoid sounding either overly optimistic or cynical - humanity is both flawed and remarkable. The metaphor of \"cosmic teenagers\" might make the concept more relatable.",
        "reasoning_details": [
          {
            "type": "reasoning.text",
            "text": "Hmm, this is a broad philosophical question. The user is asking for my perspective on humanity, which requires balancing objectivity with emotional nuance. \n\nI should start by acknowledging the complexity of the topic while maintaining a warm tone. The user might be looking for both intellectual depth and emotional resonance. \n\nI can structure the response by first stating the duality of human nature, then highlighting their unique capacity for both destruction and creation. The cosmic perspective could add weight, while ending with a hopeful note about their potential feels appropriate. \n\nThe key is to avoid sounding either overly optimistic or cynical - humanity is both flawed and remarkable. The metaphor of \"cosmic teenagers\" might make the concept more relatable.",
            "format": "unknown",
            "index": 0
          }
        ]
      }
    }
  ],
  "usage": {
    "completion_tokens": 343,
    "prompt_tokens": 256,
    "total_tokens": 599,
    "completion_tokens_details": {
      "reasoning_tokens": 141,
      "image_tokens": 0,
      "audio_tokens": 0
    },
    "prompt_tokens_details": {
      "cached_tokens": 192,
      "cache_write_tokens": 0,
      "audio_tokens": 0,
      "video_tokens": 0
    }
  },
  "meta": {
    "usage": {
      "credits_used": 1892,
      "usd_spent": 0.000946
    }
  }
}