Chat Completions

Create chat completion responses. Supports text generation, multimodal input, Function Calling, streaming, and more.

For new projects, we recommend the Responses API. The Responses API separates instructions from input, so system instructions benefit from Prompt Caching automatically, with a higher cache hit rate and noticeably lower cost and latency. Chat Completions remains supported long term; existing integrations do not need to migrate.

Endpoint


POST https://api.ofox.ai/v1/chat/completions

Request Parameters

Parameter	Type	Required	Description
`model`	string	✅	Model identifier, e.g. `openai/gpt-6.1-sol`
`messages`	array	✅	Message array
`temperature`	number	—	Sampling temperature 0-2, default 1
`max_tokens`	number	—	Maximum tokens to generate
`stream`	boolean	—	Enable streaming response
`top_p`	number	—	Nucleus sampling parameter
`frequency_penalty`	number	—	Frequency penalty -2 to 2
`presence_penalty`	number	—	Presence penalty -2 to 2
`tools`	array	—	Tool definitions (Function Calling)
`tool_choice`	string/object	—	Tool selection strategy
`response_format`	object	—	Response format (JSON Mode)
`provider`	object	—	OfoxAI extension: routing and fallback config

Message Format


interface Message {
  role: 'system' | 'user' | 'assistant' | 'tool'
  content: string | ContentPart[]  // Text or multimodal content
  name?: string
  tool_calls?: ToolCall[]          // Tool calls in assistant messages
  tool_call_id?: string            // Call ID in tool messages
}
 
// Multimodal content
type ContentPart =
  | { type: 'text'; text: string }
  | { type: 'image_url'; image_url: { url: string; detail?: 'auto' | 'low' | 'high' } }

Request Examples

cURL

Terminal


curl https://api.ofox.ai/v1/chat/completions \
  -H "Authorization: Bearer $OFOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-6.1-sol",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain what an API Gateway is"}
    ],
    "temperature": 0.7
  }'

Python

chat.py


from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.ofox.ai/v1",
    api_key="<your OFOXAI_API_KEY>"
)
 
response = client.chat.completions.create(
    model="openai/gpt-6.1-sol",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain what an API Gateway is"}
    ],
    temperature=0.7
)
 
print(response.choices[0].message.content)

TypeScript

chat.ts


import OpenAI from 'openai'
 
const client = new OpenAI({
  baseURL: 'https://api.ofox.ai/v1',
  apiKey: '<your OFOXAI_API_KEY>'
})
 
const response = await client.chat.completions.create({
  model: 'openai/gpt-6.1-sol',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Explain what an API Gateway is' }
  ],
  temperature: 0.7
})
 
console.log(response.choices[0].message.content)

Response Format


{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1703123456,
  "model": "openai/gpt-6.1-sol",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "An API Gateway is a..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 150,
    "total_tokens": 175
  }
}

Streaming

Set stream: true to enable SSE streaming responses:

Python

stream.py


stream = client.chat.completions.create(
    model="openai/gpt-6.1-sol",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)
 
for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

Streaming Response Format

Each chunk is sent via SSE:


data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":" there"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Multimodal Input (Vision)

Send images for model analysis:


response = client.chat.completions.create(
    model="openai/gpt-6.1-sol",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What's in this image?"},
            {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
        ]
    }]
)

Models with vision capabilities include openai/gpt-6.1-sol, anthropic/claude-sonnet-5.5, google/gemini-3.8-flash, and more. See the Vision guide for details.

Function Calling

See the Function Calling guide for details.