35 lines
1.2 KiB
Plaintext
Raw Normal View History

# Actions in production
## Rate limits
Consider implementing rate limiting on the API endpoints you expose. ChatGPT will respect 429 response codes and dynamically back off from sending requests to your action after receiving a certain number of 429's or 500's in a short period of time.
### Timeouts
When making API calls during the actions experience, timeouts take place if the following thresholds are exceeded:
- 45 seconds round trip for API calls
### Use TLS and HTTPS
All traffic to your action must use TLS 1.2 or later on port 443 with a valid public certificate.
### IP egress ranges
ChatGPT will call your action from an IP address from one of these [CIDR blocks](https://en.wikipedia.org/wiki/Classless_Inter-Domain_Routing):
- `23.102.140.112/28`
- `13.66.11.96/28`
- `104.210.133.240/28`
- `20.97.188.144/28`
- `20.161.76.48/28`
- `52.234.32.208/28`
- `52.156.132.32/28`
- `40.84.180.128/28`
You may wish to explicitly allowlist these IP addresses.
### How is Action data used?
Actions connect ChatGPT to external apps. If a user interacts with a GPTs custom action, ChatGPT may send parts of their conversation to the actions endpoint.