Responses
POST /v1/responses — OpenAI Responses format.
POST /v1/responses — the OpenAI Responses format, used by Codex and newer OpenAI SDK code. It works with every model in the catalog.
Example
curl https://api.aivokey.dev/v1/responses \
-H "Authorization: Bearer sk-aivo_..." \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro",
"input": "Write a haiku about caching.",
"max_output_tokens": 256
}'
Notes
- With
"stream": trueyou receiveresponse.*events, ending withresponse.completed. - If the answer is cut by
max_output_tokens, the stream ends withresponse.incomplete(incomplete_details.reason: "max_output_tokens"). - Token usage is in the final event.
- The hosted
web_searchtool is supported — see Web search & fetch.