API Reference

Boundless implements the **OpenAI API specification**. Change `base_url` and use your Boundless API key.

Boundless implements the OpenAI API specification. Change base_url and use your Boundless API key.

Base URL: https://api.boundlessapi.com/v1

Endpoints

Method Path Description
POST /chat/completions Chat completions (primary)
POST /completions Legacy completions
GET /models List available models
GET /models/{model} Model details

POST /chat/completions

Request

{
  "model": "claude-sonnet-4-6",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ],
  "temperature": 0.7,
  "max_tokens": 1024,
  "stream": false
}

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1718553600,
  "model": "claude-sonnet-4-6",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 10,
    "total_tokens": 30
  }
}

Headers

Header Required Description
Authorization Yes Bearer sk-...
Content-Type Yes application/json

Optional Parameters

Parameter Type Description
model string Model ID — see Models
messages array Chat messages
temperature number 0–2
max_tokens integer Max completion tokens
stream boolean Enable SSE streaming
tools array Function calling tools
tool_choice string/object Tool selection
response_format object JSON mode / schema
top_p number Nucleus sampling
stop string/array Stop sequences

GET /models

curl https://api.boundlessapi.com/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Returns list of available models with IDs and metadata.

Streaming

Set "stream": true. Response uses Server-Sent Events (SSE). See Streaming.

Tool Calling

Supported on compatible models. Pass tools array per OpenAI spec.

Multimodal

Image inputs supported on vision models. Pass image URL or base64 in message content per OpenAI format.

Error Format

OpenAI-compatible:

{
  "error": {
    "message": "Insufficient credits",
    "type": "insufficient_quota",
    "code": "insufficient_quota"
  }
}

See Error Codes.

Rate Limit Headers

x-ratelimit-limit-requests: 60
x-ratelimit-remaining-requests: 59
x-ratelimit-reset-requests: 1s

Related