Chat Completions

OpenAI-compatible endpoint for LLM chat. Supports streaming and tool calling. Drop-in replacement: change only the base URL and API key. On RelayDance the chat models are the Grok family (for example grok-4.3).

#Request body

Parameter	Type	Required	Description
`model`	string	Yes	Model ID from your key's model list
`messages`	array	Yes	Array of {role, content} objects. Roles: system \| user \| assistant
`temperature`	number	No	Sampling temperature 0 to 2. Default: 1
`max_tokens`	integer	No	Max tokens to generate. Model limit applies if omitted
`stream`	boolean	No	If true, stream tokens via SSE. Default: false
`top_p`	number	No	Nucleus sampling, alternative to temperature
`stop`	string \| array	No	Up to 4 stop sequences
`tools`	array	No	OpenAI tool-use schema for function calling

#Example request

terminalbash

curl https://relaydance.com/v1/chat/completions \
  -H "Authorization: Bearer $RELAYDANCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4.3",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user",   "content": "Explain quantum computing in 2 sentences."}
    ],
    "temperature": 0.7,
    "max_tokens": 256
  }'

#Response (non-streaming)

response.jsonjson

{
  "id":      "chatcmpl-abc123",
  "object":  "chat.completion",
  "created": 1749300000,
  "model":   "grok-4.3",
  "choices": [
    {
      "index":         0,
      "message":       { "role": "assistant", "content": "Quantum computing uses quantum bits..." },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens":     32,
    "completion_tokens": 48,
    "total_tokens":      80
  }
}

#Streaming

Set stream: true to receive tokens as Server-Sent Events:

stream_response.txttext

data: {"id":"chatcmpl-abc123","choices":[{"delta":{"content":"Quantum"},"index":0}]}
data: {"id":"chatcmpl-abc123","choices":[{"delta":{"content":" computing"},"index":0}]}
...
data: [DONE]

#Tool calling

tools.jsonjson

{
  "model": "grok-4.3",
  "messages": [{"role": "user", "content": "What's the weather in Tokyo?"}],
  "tools": [
    {
      "type": "function",
      "function": {
        "name":        "get_weather",
        "description": "Get the current weather for a location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {"type": "string", "description": "City name"}
          },
          "required": ["location"]
        }
      }
    }
  ]
}

Tool calling and parameter support vary by model. Unsupported parameters are ignored upstream.

←Upload Files FAQ→