OpenAI
💡
The OpenAI free tier rate limit docs (opens in a new tab)
Free Tier Limits
| MODEL | RPM | RPD | TPM | TPD |
|---|---|---|---|---|
| gpt-3.5-turbo | 3 | 200 | 40,000 | |
| text-embedding-ada-002 | 3 | 200 | 150,000 | |
| whisper-1 | 3 | 200 | ||
| tts-1 | 3 | 200 | ||
| dall-e-2 | 5 | img/min | ||
| dall-e-3 | 1 | img/min |
*RPM is the key figure for Stratus at the moment.
Assuming GPT 3.5 Turbo within free tier, you would want to avoid being rate limited 3 reqs/min should mean your RateLimitConfigOptions config will be:
const rateLimited = await client.rateLimit({
limit: 2,
window: 60,
});