API Reference

OpenAI-compatible endpoints for DeepSeek models

Base URL: https://vorara.com/v1

Authentication

All requests require a Bearer token in the Authorization header:

Authorization: Bearer <your-api-token>

Get your token from the Dashboard.

Models & Pricing

Model ID	Input / 1M	Output / 1M	Context
deepseek-chat	$0.14	$0.28	1M
deepseek-reasoner	$2.20	$4.20	1M

Endpoints

GET/v1/models

List all available models.

curl https://vorara.com/v1/models -H "Authorization: Bearer <token>"

Response:

{
  "object": "list",
  "data": [
    {"id": "deepseek-chat", "object": "model"},
    {"id": "deepseek-reasoner", "object": "model"}
  ]
}

POST/v1/chat/completions

Create a chat completion. Compatible with OpenAI API format.

Parameters: model, messages, max_tokens, temperature, stream

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "model": "deepseek-v4-flash",
  "choices": [{
    "index": 0,
    "message": {"role": "assistant", "content": "Hello!"},
    "finish_reason": "stop"
  }],
  "usage": {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15}
}

SSE/v1/chat/completions (stream)

Set stream: true for Server-Sent Events streaming responses.

data: {"choices":[{"delta":{"content":"Hello"},"index":0}]}

data: {"choices":[{"delta":{"content":" world"},"index":0}]}

data: [DONE]

Quick Start

curl https://vorara.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <token>" \
  -d '{"model":"deepseek-chat","messages":[{"role":"user","content":"Hello"}],"max_tokens":100}'

Error Codes

HTTP	Meaning	Action
400	Bad request	Check JSON format and model name
401	Unauthorized	Token missing or invalid
403	Forbidden	Token quota exhausted or disabled
429	Rate limited	Reduce request frequency
500	Server error	Retry or contact support
503	Service unavailable	Upstream API unreachable

Rate Limits

60 req/min

Per IP address

50 conn

Concurrent per IP

10MB

Max request body

300s

Request timeout