Messages

UI completions are returned by the API when stream=false is set in the request.

Request Headers

Authorization · string · required

The API key to use for the request.

Content-Type · string · required

The content type of the request. Should be application/json.

Request Body

messages · array · required

An array of messages of the conversation so far.

Show Message Properties

message.role · string

The role of the message. Can be either user, assistant, or tool.

message.content · string

The content of the message.

message.tool_call_id · string

The ID of the tool call. Only present if the role is tool.

model · string · required

The model to use for the UI completion. Should be one of the models listed in the Models page.

temperature · number

The temperature to use for the UI completion. Should be between 0 and 1.

top_p · number

The top-p value to use for the UI completion. Should be between 0 and 1.

max_tokens · integer

The maximum number of tokens to use for the UI completion.

n · integer

The number of completions to generate.

stop · integer

Should be unset or set to 1.

stream · boolean

Whether to stream the response. Should be unset or false.

The parameters above are commonly used with the Messages API. For a comprehensive list of all supported parameters and their compatibility across different model providers (OpenAI vs Anthropic), see the Supported API Parameters table.

curl

curl -X POST \
  -H "Authorization: Bearer <api_key>" \
  -H "Content-Type: application/json" \
  -d '{"model": "c1/anthropic/claude-sonnet-4/v-20251230", "messages": [{"role": "user", "content": "Hello, world!"}]}' \
  https://api.thesys.dev/v1/embed/chat/completions

{
      "id": "chatcmpl-1743157633416-cffw7tgswx",
      "object": "chat.completion",
      "created": 1743157633,
      "model": "c1/anthropic/claude-sonnet-4/v-20251230",
      "choices": [
          {
          "index": 0,
          "message": {
              "role": "assistant",
              "content": {
                  ...
              }
          },
          "finish_reason": "stop"
          }
      ],
      "usage": {
          "prompt_tokens": 8,
          "completion_tokens": 439,
          "total_tokens": 447
      }
}

Response

id · string

A unique identifier for the UI completion

choices · array

An array of completions. Will always contain exactly one object.

Show Properties

finish_reason · string

The reason the generation stopped. Can be either stop or tool_calls.

message · object

Completion message generated by the model.

Show Properties

message.role · string

The role of the message. Will always be assistant for generations.

message.content · string

A JSON object containing the UI completion.

created · string

The timestamp when the UI completion was created

model · string

The model used to generate the UI completion

object · string

The object type, which is always chat.completion

usage · object

An object containing the usage statistics for the UI completion

Show Properties

usage.prompt_tokens · integer

Number of tokens in the prompt

usage.completion_tokens · integer

Number of tokens in the generated UI completion

usage.total_tokens · integer

Total number of tokens: prompt_tokens + completion_tokens