Create a response
Create a response using the OpenRoute Responses API. Supports streaming and provider-specific parameters.
Last updated on
Create a response using the OpenRoute Responses API. Supports streaming and provider-specific parameters.
Last updated on
When true, returns Server-Sent Events stream.
falseUse to continue a session with the same deployment.
Maximum number of output tokens to generate (OpenAI/Anthropic compatible).
1 <= valueProvider-specific request parameters.
OpenAI-compatible options. All OpenAI Responses API parameters are supported.
0 <= value <= 20 <= value <= 1curl -X POST "https://api.openroute.cn/responses" \ -H "Content-Type: application/json" \ -d '{ "model": "openai/o1-pro", "input": "Tell me a three sentence bedtime story about a unicorn.", "max_output_tokens": 100 }'Target model identifier (may include provider prefix like openai/, anthropic/, vertex_ai/, bedrock/, gemini/).
Input prompt or structured content.
curl -X POST "https://api.openroute.cn/responses" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/o1-pro",
"input": "Tell me a three sentence bedtime story about a unicorn.",
"max_output_tokens": 100
}'Anthropic-compatible options subset.
Vertex AI Gemini-compatible options subset.
AWS Bedrock-compatible options subset.
Google AI Studio-compatible options subset.
{
"id": "string",
"model": "string",
"output": [
{
"type": "message",
"content": [
{
"
{
"type": "string",
"title": "string"
}{
"type": "string",
"title": "string"
}{
"type": "string",
"title": "string"
}