Create Message

Anthropic-compatible Messages endpoint. Supports OpenAI-style messages as input and can return OpenAI-style responses when response_format=‘openai’ is provided.

POST /v1/messages

cURL

curl --request POST \
  --url 'http://localhost:8000/v1/messages' \
  --header "Authorization: Bearer $STATESET_AGENTS_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "string",
  "messages": [
    {
      "role": "system",
      "content": "Two-person tent, green — replacement for damaged pole set.",
      "name": "Two-Person Tent",
      "tool_call_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
      "tool_calls": []
    }
  ],
  "system": "string",
  "max_tokens": 1,
  "temperature": 1.5,
  "top_p": 1.5,
  "top_k": 1,
  "stop_sequences": [
    "string"
  ],
  "stream": false,
  "tools": [
    {}
  ],
  "tool_choice": "string",
  "metadata": {},
  "response_format": "anthropic"
}'

200

{
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "type": "message",
  "role": "assistant",
  "model": "string",
  "content": [
    {}
  ],
  "stop_reason": "string",
  "stop_sequence": "string",
  "usage": {
    "input_tokens": 1,
    "output_tokens": 1
  }
}

Anthropic-compatible Messages endpoint.

Supports OpenAI-style messages as input and can return OpenAI-style responses when response_format='openai' is provided.

Request body

MessagesRequest

model · string · required

Model identifier

messages · MessageInput[] · required

Conversation messages

system · string

System prompt (string or content blocks)

max_tokens · integer,null

Maximum tokens to generate

temperature · number,null

Sampling temperature

top_p · number,null

Top-p

top_k · integer,null

Top-k

stop_sequences · string[],null

Stop sequences (Anthropic style)

stream · boolean

Stream response tokens

tools · object[],null

Tool definitions (Anthropic or OpenAI format)

tool_choice · string

Tool choice configuration

metadata · object,null

Arbitrary metadata

response_format · string,null

Response format preference

Response

MessagesResponse

id · string · required

Message identifier

type · string

Response type

role · string

Assistant role

model · string · required

Model identifier

content · object[] · required

Response content blocks

stop_reason · string,null

Stop reason

stop_sequence · string,null

Stop sequence

usage · UsageInfo · required

Token usage

Show UsageInfo

input_tokens · integer · required

Prompt tokens used

output_tokens · integer · required

Completion tokens used

Status codes

Code	Meaning
200	Anthropic-shaped reply. With response_format: 'openai' the body is an OpenAI chat completion instead; with stream: true it is a text/event-stream.
401	Authentication required
422	Validation Error
429	Rate limit exceeded

cURL

curl --request POST \
  --url 'http://localhost:8000/v1/messages' \
  --header "Authorization: Bearer $STATESET_AGENTS_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "string",
  "messages": [
    {
      "role": "system",
      "content": "Two-person tent, green — replacement for damaged pole set.",
      "name": "Two-Person Tent",
      "tool_call_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
      "tool_calls": []
    }
  ],
  "system": "string",
  "max_tokens": 1,
  "temperature": 1.5,
  "top_p": 1.5,
  "top_k": 1,
  "stop_sequences": [
    "string"
  ],
  "stream": false,
  "tools": [
    {}
  ],
  "tool_choice": "string",
  "metadata": {},
  "response_format": "anthropic"
}'

200

{
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "type": "message",
  "role": "assistant",
  "model": "string",
  "content": [
    {}
  ],
  "stop_reason": "string",
  "stop_sequence": "string",
  "usage": {
    "input_tokens": 1,
    "output_tokens": 1
  }
}