curl --request POST \
--url https://api.shuyou.ai/openrouter/v1/responses \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "openai/gpt-5.5-pro",
"input": "Hello!"
}
'{
"id": "resp_example",
"object": "response",
"created_at": 1741569952,
"status": "completed",
"model": "openai/gpt-5.5-pro",
"output": [
{
"type": "message",
"id": "msg_example",
"role": "assistant",
"status": "completed",
"content": [
{
"type": "output_text",
"text": "Hello! How can I help you today?",
"annotations": []
}
]
}
],
"usage": {
"input_tokens": 19,
"output_tokens": 10,
"total_tokens": 29
}
}OpenRouter
Create a Response
Create a model response using the OpenRouter-compatible Responses API on ShuYou.
POST
/
openrouter
/
v1
/
responses
curl --request POST \
--url https://api.shuyou.ai/openrouter/v1/responses \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "openai/gpt-5.5-pro",
"input": "Hello!"
}
'{
"id": "resp_example",
"object": "response",
"created_at": 1741569952,
"status": "completed",
"model": "openai/gpt-5.5-pro",
"output": [
{
"type": "message",
"id": "msg_example",
"role": "assistant",
"status": "completed",
"content": [
{
"type": "output_text",
"text": "Hello! How can I help you today?",
"annotations": []
}
]
}
],
"usage": {
"input_tokens": 19,
"output_tokens": 10,
"total_tokens": 29
}
}Overview
OpenResponses-format API routed through OpenRouter on ShuYou. Supports streaming and non-streaming output.Request parameters follow the OpenRouter official API exactly. ShuYou only routes and forwards your request — all client parameters are preserved.
https://api.shuyou.ai/openrouter
Endpoint: POST /v1/responsesAuthorizations
Authorization: Bearer YOUR_API_KEY
Body
application/json
Model ID (provider/model_name). Use the slug from List Models.
Example:
"openai/gpt-5.5-pro"
Plain-text input (equivalent to a single user message).
System/developer instructions. Not carried over when using previous_response_id.
ID of the previous response for multi-turn conversations. Cannot be used with conversation.
Associates this response with a conversation.
Reference a prompt template and variables.
Show child attributes
Show child attributes
Additional output data to include in the response.
Available options:
web_search_call.action.sources, computer_call_output.output.image_url, message.input_image.image_url, message.output_text.logprobs, reasoning.encrypted_content Upper bound for generated tokens, including visible output and reasoning tokens.
Maximum total built-in tool calls processed in this response.
Whether to allow parallel tool calls.
Reasoning model configuration.
Show child attributes
Show child attributes
Text output configuration (plain text or structured JSON).
Show child attributes
Show child attributes
Required range:
0 <= x <= 2Required range:
0 <= x <= 1Required range:
0 <= x <= 20Context truncation when input exceeds the context window.
Available options:
auto, disabled Tools the model may call. ShuYou does not support file_search, code_interpreter, or image_generation tools.
- Option 1
- Option 2
- Option 3
- Option 4
- Option 5
- Option 6
- Option 7
- Option 8
- Option 9
Show child attributes
Show child attributes
Available options:
none, auto, required Whether to store the response for later retrieval.
Stream the response via server-sent events.
Show child attributes
Show child attributes
Cache key for similar requests (replaces legacy user).
Available options:
in_memory, 24h Stable hashed user identifier for abuse detection.
Maximum string length:
64ShuYou: multi-provider routing.
Show child attributes
Show child attributes
ShuYou: model selection within a provider.
Show child attributes
Show child attributes
Response
Response object, or SSE stream when stream is true