Responses
Responses API endpoints
Create response
Authorization
bearerAuth API key in format: eur_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
In: header
Request Body
application/json
Fallback model list (EUrouter extension)
Routing rule ID to apply (EUrouter extension)
^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$uuidRouting rule name to apply (EUrouter extension)
Provider routing preferences (EUrouter extension)
Model identifier (e.g., "gpt-4o")
The input to generate a response for
System-level instructions for the model
ID of previous response for conversation continuity
Enable streaming responses
Options for streaming responses
Maximum tokens to generate
Sampling temperature (0-2)
Nucleus sampling probability (0-1)
Available tools for the model
Tool calling behavior
Allow parallel tool calls
Context truncation strategy
"auto" | "disabled"Custom metadata
End-user identifier for abuse detection
Whether to store the response
Reasoning parameters (for reasoning models)
Text format specification
Whether to run the response in the background
Additional output data to include
Maximum number of tool calls allowed
Service tier for the request
"auto" | "default" | "flex"Response Body
application/json
curl -X POST "https://api.eurouter.ai/api/v1/responses" \ -H "Content-Type: application/json" \ -d '{ "input": "string" }'{
"id": "string",
"object": "response",
"created_at": 0,
"status": "queued",
"model": "string",
"output": [
{
"type": "message",
"id": "string",
"role": "assistant",
"status": "in_progress",
"content": [
{
"type": "output_text",
"text": "string",
"annotations": [
null
],
"logprobs": [
null
]
}
]
}
],
"usage": {
"input_tokens": 0,
"output_tokens": 0,
"total_tokens": 0,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens_details": {
"reasoning_tokens": 0
}
},
"completed_at": 0,
"error": {
"code": "string",
"message": "string"
},
"incomplete_details": {
"reason": "max_output_tokens"
},
"instructions": "string",
"max_output_tokens": 0,
"parallel_tool_calls": true,
"previous_response_id": "string",
"reasoning": {
"effort": "low",
"summary": "auto"
},
"store": true,
"temperature": 0,
"text": {
"format": {
"type": "text"
},
"verbosity": "auto"
},
"tool_choice": "string",
"tools": [
null
],
"top_p": 0,
"truncation": "auto",
"user": "string",
"metadata": {
"property1": "string",
"property2": "string"
},
"background": true,
"service_tier": "string"
}