Chat Completions

POST https://routify.bytedance.city/v1/chat/completions

OpenAI-compatible. Drop-in replacement for api.openai.com.

Request

POST /v1/chat/completions
Authorization: Bearer rtf_xxx
Content-Type: application/json
 
{
  "model": "deepseek-v3.2",
  "messages": [
    {"role": "system", "content": "You are concise."},
    {"role": "user", "content": "Capital of France?"}
  ],
  "temperature": 0.3,
  "max_tokens": 256,
  "stream": false
}

Parameters

Param	Type	Default	Notes
`model`	string	required	Model name (see Models) or `routify-auto`
`messages`	array	required	OpenAI-style messages
`temperature`	number	1	0–2, lower = more deterministic
`top_p`	number	1	Alternative to temperature
`max_tokens`	int	model max	Hard cap on completion
`stream`	bool	false	SSE streaming
`stop`	string \| array	null	Stop sequences
`tools`	array	—	Function calling (see Quickstart)
`tool_choice`	string \| object	auto	Force a specific tool
`response_format`	object	—	`{"type": "json_object"}` for JSON mode
`extra_body.routify`	object	—	Routify-specific opts (region, task)

Response

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1747836000,
  "model": "deepseek-v3.2",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Paris."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 2,
    "total_tokens": 16
  },
  "routify": {
    "channel": "deepseek-official",
    "latency_ms": 187,
    "cost_usd": 0.0000028
  }
}

Streaming

Set stream: true. Each line is data: <json> SSE:

data: {"id":"...","choices":[{"delta":{"content":"Hello"}}]}
data: {"id":"...","choices":[{"delta":{"content":" world"}}]}
data: [DONE]

Errors

Code	Reason
400	Invalid request body
401	Missing / invalid API key
402	Insufficient balance
403	Account suspended / model not allowed for tier
429	Rate limit
500	Internal error
502	All upstream channels failed
503	Maintenance

Pricing Embeddings