Responses (Preview)
POST/api/v2/inference/:vendor/:model/responses
> 🧪 Preview — This endpoint is in preview and its contract may change.
Creates a model response for the given input using an OpenAI-compatible Responses API. Serenity Cloud models are exposed as OpenAI-compatible endpoints, so you can call them with the OpenAI SDKs by pointing the base URL at this route and passing your Serenity API key as a Bearer token.
When stream is true, the response is delivered as Server-Sent Events (SSE).
Request​
Path Parameters
Possible values: [qwen]
The model vendor. Currently available: qwen.
Possible values: [qwen3.6, qwen3.6-27b, qwen3.6-35b-a3b]
The model identifier. Currently available models for qwen: qwen3.6, qwen3.6-27b, qwen3.6-35b-a3b. This list grows as models are deployed.
Query Parameters
Use this param to override the culture of the response. Options: - en (default) - es
- application/json
Body
required
- ResponseTextFormatConfigurationText
- ResponseTextFormatConfigurationJsonObject
- ResponseTextFormatConfigurationJsonSchema
input
object
required
agent
object
reasoning
object
metadata
object
nullable
conversation
object
metadata
object
nullable
prompt
object
variables
object
nullable
stream_options
object
text
object
format
object
nullable
oneOf
Responses​
- 200
- 400
- 401
- 403
- 500
OK
There was a validation error. Please check your request data.
- application/json
- Schema
- Example (from schema)
Schema
errors
object
nullable
{
"message": "string",
"errors": {}
}
The user is unauthorized or the session expired
The user does not have permission
There was an unexpected error