Anthropic

POST

/v1/messages

curl --request POST \
  --url https://coder.api.visioncoder.cn/v1/messages \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{ "model": "claude-sonnet-5", "messages": [ { "role": "user", "content": "Hello" } ], "max_tokens": 4096, "system": "You are a concise assistant.", "temperature": 1, "top_p": 1, "top_k": 1, "stop_sequences": [ "example" ], "stream": false, "tools": [ {} ], "tool_choice": {}, "metadata": { "user_id": "example" } }'

• Production

Authorizations

• BearerAuth

Request Body^required

Media typeapplication/json

AnthropicProvidersReq

Anthropic Messages API request body. The platform forwards it upstream as-is; fields follow the official Anthropic protocol.

object

model

required

Model ID supporting the Anthropic protocol — Claude models (claude-sonnet-5, claude-opus-5, claude-haiku-4-5-20251001, claude-opus-4-8, claude-opus-4-8, claude-haiku-4-5-20251001) and all open-source models (deepseek-v4-pro, deepseek-v4-flash, qwen3.6-35b-a3b, kimi-k2.6, glm-5.1, glm-5.2, minimax-m2.7). Call GET /v1/models for the live list.

string

Example

claude-sonnet-5

messages

required

Array<object>

object

role

required

string

Allowed values: user assistant

Example

user

content

required

String, or an array of structured items with type=text/image/tool_use/tool_result

Example

Hello

max_tokens

required

integer

Example

4096

system

String or structured array, used as the system prompt

Example

You are a concise assistant.

temperature

number format: float

<= 1

top_p

number format: float

top_k

integer

stop_sequences

Array<string>

stream

boolean

tools

Array<object>

object

tool_choice

object

metadata

object

user_id

string

Responses

200

A successful response.

Media typeapplication/json

AnthropicProvidersResp

Anthropic Messages API response body.

object

id

string

type

string

role

string

model

string

content

Array<object>

object

type

string

Allowed values: text tool_use

text

string

stop_reason

string

Allowed values: end_turn max_tokens stop_sequence tool_use

stop_sequence

string

usage

object

input_tokens

integer

output_tokens

integer

cache_creation_input_tokens

integer

cache_read_input_tokens

integer

Example

{
  "id": "msg_01XYZ",
  "type": "message",
  "role": "assistant",
  "model": "claude-sonnet-5",
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I help you?"
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 12,
    "output_tokens": 28
  }
}