POST
/
v1
/
messages
curl -X POST https://api.example.com/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -d '{
    "model": "claude-haiku-4-5-20251001",
    "max_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": "Hello, Claude!"
      }
    ]
  }'

{
  "id": "msg_01XFDUDYJgAACzvnptvVoYEL",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I help you today?"
    }
  ],
  "model": "claude-haiku-4-5-20251001",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 10,
    "output_tokens": 12
  }
}
Official documentation: https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking
Create model responses for given messages using Anthropic Claude models.

​
Request Parameters

​
model
string
required
The model to use. Available models include:
  • claude-haiku-4-5-20251001
  • claude-sonnet-4-20250514
  • claude-opus-4-5-20251101
​
max_tokens
integer
required
The maximum number of tokens to generate before stopping.
​
messages
array
required
Input messages. Each message has a role and content.content can be:
  • A string for simple text messages
  • An array of content blocks for multimodal input (text, images, documents)
​
temperature
number
default:"1"
Amount of randomness injected into the response. Ranges from 0.0 to 1.0.
​
top_p
number
Use nucleus sampling. Only sample from the top P probability mass.
​
top_k
integer
Only sample from the top K options for each subsequent token.
​
stream
boolean
default:"false"
Whether to incrementally stream the response using server-sent events.
​
system
string
System prompt that sets context and instructions for the model.

​
Multimodal Content

Claude supports various content types in messages:

​
Text Content

{
  "type": "text",
  "text": "Your message here"
}

​
Image Content

{
  "type": "image",
  "source": {
    "type": "base64",
    "media_type": "image/jpeg",
    "data": "base64_encoded_image_data"
  }
}

​
Document Content (PDF)

{
  "type": "document",
  "source": {
    "type": "base64",
    "media_type": "application/pdf",
    "data": "base64_encoded_pdf_data"
  },
  "cache_control": {
    "type": "ephemeral"
  }
}

​
Response

​
id
string
Unique identifier for the message.
​
type
string
Object type, which is message.
​
role
string
Role of the generated message, which is assistant.
​
content
array
Content generated by the model.
​
model
string
The model that processed the request.
​
stop_reason
string
The reason the model stopped generating.
​
usage
object
Token usage information.
curl -X POST https://api.example.com/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -d '{
    "model": "claude-haiku-4-5-20251001",
    "max_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": "Hello, Claude!"
      }
    ]
  }'

{
  "id": "msg_01XFDUDYJgAACzvnptvVoYEL",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I help you today?"
    }
  ],
  "model": "claude-haiku-4-5-20251001",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 10,
    "output_tokens": 12
  }
}