Skip to main content
POST
https://serverless.tensormesh.ai
/
v1
/
responses
Create Response
curl --request POST \
  --url https://serverless.tensormesh.ai/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/gpt-oss-20b",
  "input": "Say hello."
}
'
{
  "id": "resp_123",
  "object": "response",
  "model": "<string>",
  "output": [
    {
      "id": "out_123",
      "type": "message",
      "role": "<string>",
      "status": "<string>",
      "content": [
        {
          "type": "output_text",
          "text": "hello",
          "annotations": [
            {}
          ]
        }
      ]
    }
  ],
  "created_at": 123,
  "status": "<string>"
}
Use this page when you want the verified serverless responses endpoint over raw HTTP.
  • Auth: Authorization: Bearer <API_KEY>
  • Host: https://serverless.tensormesh.ai
  • Model: pass a serverless model name in the JSON request body
If you are choosing between raw HTTP and the Python SDK, the matching SDK namespace is client.inference.serverless.responses.

Authorizations

Authorization
string
header
required

Bearer authentication using your serverless API key. Format: Bearer <API_KEY>

Body

application/json
model
string
required

Serverless model name to use.

Example:

"openai/gpt-oss-20b"

input
any
required

Input passed to the responses endpoint.

max_output_tokens
integer

Optional limit for generated output tokens.

Response

Successful Response

id
string
required
Example:

"resp_123"

object
string
required
Example:

"response"

model
string
required
output
ResponseOutputItem · object[]
required
created_at
integer
status
string | null