API Overview

Base URL

All API requests should be made to:

https://www.tokiai.ai/v1

Request Format

All requests must use HTTPS
Request bodies should be JSON-encoded
Include Content-Type: application/json header
Include Authorization: Bearer YOUR_API_KEY header

Response Format

Chat completion responses follow the common OpenAI Chat Completions structure:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1714000000,
  "model": "deepseek/deepseek-chat-v3",
  "choices": [...],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

Error Handling

Errors generally return appropriate HTTP status codes with a JSON error body:

Status Code	Description
400	Bad Request — Invalid parameters
401	Unauthorized — Invalid API key
403	Forbidden — Insufficient permissions
429	Too Many Requests — Rate limit exceeded
500	Internal Server Error

{
  "error": {
    "code": "invalid_request",
    "message": "The 'model' field is required.",
    "type": "invalid_request_error"
  }
}

Different models, quota states, and API key states may return different messages. Clients should read error.message and handle it together with the HTTP status code.

Common Endpoints

Method	Path	Description
`POST`	`/chat/completions`	Create a chat completion.
`GET`	`/models`	List currently available models; availability depends on the current server implementation.

Streaming

TOKI supports server-sent events (SSE) for streaming responses. Set stream: true in your request:

const stream = await openai.chat.completions.create({
  model: 'deepseek/deepseek-chat-v3',
  messages: [{ role: 'user', content: 'Tell me a story' }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}