Create a message (Anthropic Messages API)

POST

{base_url}

messages

Error

A valid request URL is required to generate request examples

{
  "content": [
    {
      "id": "<string>",
      "input": {},
      "name": "<string>",
      "text": "<string>",
      "thinking": "<string>",
      "type": "<string>"
    }
  ],
  "id": "<string>",
  "model": "<string>",
  "role": "<string>",
  "stop_reason": "<string>",
  "stop_sequence": "<string>",
  "type": "<string>",
  "usage": {
    "cache_creation_input_tokens": 123,
    "cache_read_input_tokens": 123,
    "input_tokens": 123,
    "output_tokens": 123
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>"
  },
  "type": "<string>"
}

{
  "error": {
    "message": "<string>",
    "type": "<string>"
  },
  "type": "<string>"
}

{
  "error": {
    "message": "<string>",
    "type": "<string>"
  },
  "type": "<string>"
}

{
  "error": {
    "message": "<string>",
    "type": "<string>"
  },
  "type": "<string>"
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Anthropic Messages request

max_tokens

integer

messages

object[]

Show child attributes

metadata

object

Show child attributes

model

string

stop_sequences

string[]

stream

boolean

system

temperature

number

thinking

object

Show child attributes

tool_choice

object

Show child attributes

tools

object[]

Show child attributes

top_k

integer

top_p

number

Response

JSON response or SSE stream when stream=true

content

object[]

Show child attributes

string

model

string

role

string

stop_reason

string

stop_sequence

string

type

string

usage

object

Show child attributes

/v1/messages/count_tokensReturns a provider-agnostic heuristic estimate of the input token count.

⌘I

Error

A valid request URL is required to generate request examples

{
  "content": [
    {
      "id": "<string>",
      "input": {},
      "name": "<string>",
      "text": "<string>",
      "thinking": "<string>",
      "type": "<string>"
    }
  ],
  "id": "<string>",
  "model": "<string>",
  "role": "<string>",
  "stop_reason": "<string>",
  "stop_sequence": "<string>",
  "type": "<string>",
  "usage": {
    "cache_creation_input_tokens": 123,
    "cache_read_input_tokens": 123,
    "input_tokens": 123,
    "output_tokens": 123
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>"
  },
  "type": "<string>"
}

{
  "error": {
    "message": "<string>",
    "type": "<string>"
  },
  "type": "<string>"
}

{
  "error": {
    "message": "<string>",
    "type": "<string>"
  },
  "type": "<string>"
}

{
  "error": {
    "message": "<string>",
    "type": "<string>"
  },
  "type": "<string>"
}