Create Chat Completion
POST /v1/chat/completions
Authentication
Pass the API Key in the request header:
Authorization: Bearer YOUR_API_KEY
Request Parameters
| Parameter | Type | Required | Default | Description |
|---|
model | string | Yes | - | Model name, e.g. gpt-4o, claude-sonnet-4-20250514, gemini-2.5-flash |
messages | array | Yes | - | Message list, each message contains role and content |
temperature | number | No | 1 | Sampling temperature, range 0-2. Higher values produce more random output |
top_p | number | No | 1 | Nucleus sampling parameter, range 0-1. Use either this or temperature |
n | integer | No | 1 | Number of responses to generate |
stream | boolean | No | false | Whether to enable streaming output |
stream_options | object | No | null | Streaming options. Set {"include_usage": true} to return usage in the last chunk |
stop | string|array | No | null | Stop generation tokens, up to 4 |
max_tokens | integer | No | Model default | Maximum number of tokens to generate |
presence_penalty | number | No | 0 | Presence penalty, range -2.0 to 2.0 |
frequency_penalty | number | No | 0 | Frequency penalty, range -2.0 to 2.0 |
logprobs | boolean | No | false | Whether to return logprobs |
top_logprobs | integer | No | null | Number of top logprobs to return, 0-20 |
response_format | object | No | null | Specify output format, e.g. {"type": "json_object"} |
seed | integer | No | null | Random seed for reproducible output |
tools | array | No | null | Available tools list (Function Calling) |
tool_choice | string|object | No | ”auto” | Tool selection strategy |
user | string | No | null | End-user identifier |
[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello"},
{"role": "assistant", "content": "Hello! How can I help you?"},
{"role": "user", "content": "Tell me about yourself"}
]
system, user, assistant, tool.
Non-Streaming Request
curl https://crazyrouter.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "gpt-4o",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Explain artificial intelligence in one sentence"}
],
"temperature": 0.7
}'
Non-Streaming Response
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"created": 1709123456,
"model": "gpt-4o",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Artificial intelligence is the technology that enables computers to simulate human intelligent behavior, allowing machines to learn, reason, and solve problems."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 28,
"completion_tokens": 32,
"total_tokens": 60
}
}
Streaming Request
curl https://crazyrouter.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "gpt-4o",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Explain artificial intelligence in one sentence"}
],
"stream": true,
"stream_options": {"include_usage": true}
}'
Streaming Response
data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1709123456,"model":"gpt-4o","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}
data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1709123456,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":"Artificial intelligence"},"finish_reason":null}]}
data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1709123456,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":" is"},"finish_reason":null}]}
data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1709123456,"model":"gpt-4o","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1709123456,"model":"gpt-4o","choices":[],"usage":{"prompt_tokens":28,"completion_tokens":32,"total_tokens":60}}
data: [DONE]
When stream_options.include_usage is set to true, the last chunk will contain the complete usage information.
The max_tokens parameter limits the number of output tokens, not including input. If the output is truncated, finish_reason will return length.
