Chat with GPT-4o-mini

POST 
/api/gpt/v1/chat

Send a message to GPT-4o-mini and receive an AI-generated response

Request

Responses

200

Success response - Chat with GPT-4o-mini

429

Too Many Requests. The rate limit has been exceeded.

Response Headers

RateLimit-Policy

The rate limit policy. Format: limit;w=window. limit is the max requests, w is the window in seconds. The specify value should be set in the .env-RATE_LIMIT_XXX

RateLimit

The current rate limit state. remaining is the remaining quota, reset is the seconds until reset. The specify value should be set in the .env-RATE_LIMIT_XXX