POST
/
v1
/
chat
/
completions
curl -X POST https://api.example.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful AI assistant."
      },
      {
        "role": "user",
        "content": "Hello, Claude!"
      }
    ],
    "max_tokens": 1024,
    "temperature": 0.7
  }'

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "claude-sonnet-4-20250514",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 10,
    "total_tokens": 30
  }
}
Official documentation: https://docs.anthropic.com/en/api/messages
Create model responses for chat conversations using Anthropic Claude models with OpenAI-compatible API format. This endpoint provides compatibility with OpenAI’s chat completions API while using Claude models.

​
Request Parameters

​
model
string
required
The model to use. Available Claude models include:
  • claude-haiku-4-5-20251001
  • claude-sonnet-4-20250514
  • claude-opus-4-5-20251101
​
messages
array
required
Array of message objects comprising the conversation. Each message has:
  • role: Either “system”, “user”, or “assistant”
  • content: The message content (string or array for multimodal)
​
max_tokens
integer
The maximum number of tokens to generate. Defaults to model’s maximum.
​
temperature
number
default:"1"
Sampling temperature between 0 and 2. Higher values make output more random.
​
top_p
number
Nucleus sampling parameter. Only sample from the top P probability mass.
​
stream
boolean
default:"false"
Whether to stream back partial progress using server-sent events.
​
stop
string | array
Up to 4 sequences where the API will stop generating further tokens.
​
presence_penalty
number
default:"0"
Number between -2.0 and 2.0. Penalizes new tokens based on presence in text.
​
frequency_penalty
number
default:"0"
Number between -2.0 and 2.0. Penalizes tokens based on frequency in text.

​
Vision Support

Claude supports image understanding through multimodal content. Include images in the content array: 
{
  "role": "user",
  "content": [
    {
      "type": "text",
      "text": "What's in this image?"
    },
    {
      "type": "image_url",
      "image_url": {
        "url": "https://example.com/image.jpg"
      }
    }
  ]
}

​
Response

​
id
string
Unique identifier for the completion.
​
object
string
Object type, which is chat.completion.
​
created
integer
Unix timestamp of when the completion was created.
​
model
string
The model used for completion.
​
choices
array
List of completion choices.
​
usage
object
Token usage information.
curl -X POST https://api.example.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful AI assistant."
      },
      {
        "role": "user",
        "content": "Hello, Claude!"
      }
    ],
    "max_tokens": 1024,
    "temperature": 0.7
  }'

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "claude-sonnet-4-20250514",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 10,
    "total_tokens": 30
  }
}