Responses | Linkinfra API Docs

POST/v1/responses

Base URLhttps://api.linkinfra.ai

Authorization Body Response

Authorization

Bearer Token

AuthorizationBearer <token>

Authenticate requests with your API key in the request header:

Authorization: Bearer sk-your-api-key

Need a key? Create one in the console

Request body

application/json

modelstringrequired

Model ID from the model catalog. Availability depends on your account group and configured channels.

inputstring | arrayrequired

Text input or structured input items.

instructionsstring

System instructions that guide model behavior.

streamboolean

Set to true to receive incremental Server-Sent Events. Defaults to false.

max_output_tokensinteger

Maximum number of output tokens.

previous_response_idstring

Link a previous response. Availability depends on the upstream channel.

Streaming

Streaming uses named SSE events such as response.output_text.delta and response.completed. The event format differs from Chat Completions.

Response

application/json

200Successful response

outputarray<object>

Output items. Text message content contains output_text.

statusstring

Response status, such as completed.

usageobject

Token usage for this request. Check usage logs in the console for actual charges.

Request failed? Read the error handling guide

curl --request POST 'https://api.linkinfra.ai/v1/responses' \ --header "Authorization: Bearer $LINKINFRA_API_KEY" \ --header "Content-Type: application/json" \ --data '{ "model": "gpt-4o-mini", "input": "Explain what an API is in one sentence.", "stream": false }'

{ "id": "resp_example", "object": "response", "status": "completed", "model": "gpt-4o-mini", "output": [ { "type": "message", "role": "assistant", "content": [ { "type": "output_text", "text": "An API lets applications communicate through a defined interface." } ] } ], "usage": { "input_tokens": 13, "output_tokens": 12, "total_tokens": 25 } }