Request Parameters
ShareKiteRouter accepts the OpenAI-compatible chat completion payload and forwards it to the selected upstream OpenAI-compatible provider route.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | ✅ | KiteRouter model ID, for example gpt-4o-mini. This can map to one or more provider models. |
messages | array | ✅ | Ordered chat messages with role and content. |
stream | boolean | — | If true, returns Server-Sent Events. Default: false. |
temperature | number | — | Sampling temperature. Forwarded as-is to the upstream provider. |
max_tokens | integer | — | Maximum output tokens when supported by the upstream provider. |
top_p | number | — | Nucleus sampling threshold. Forwarded as-is. |
stop | string | array | — | Stop sequence(s). Forwarded as-is. |
tools | array | — | OpenAI-compatible tool definitions for models that support tool calling. |
tool_choice | string | object | — | Tool selection behavior. Forwarded as-is. |
response_format | object | — | JSON mode / structured output options when supported by the model. |
Message Format
1{ 2 "role": "user", 3 "content": "Your message here" 4}
Roles
| Role | Description |
|---|---|
system | Sets assistant behavior. KiteRouter may inject an admin-configured system prompt before forwarding. |
user | User input. |
assistant | Previous assistant response for conversation context. |
tool | Tool result messages when using OpenAI-compatible tool calling. |
Info: KiteRouter does not convert request formats. Use OpenAI-compatible payloads for /api/v1/chat/completions.