Routing and reliability
Rate limits
The tiers, windows and counting rules behind the gateway's own 429s.
このページはまだ翻訳されていません。英語版を表示しています。
Every organization has a rate-limit tier. The tier sets requests per minute and tokens per minute, hour and day for platform-funded traffic, counted across every key in the organization. Traffic on your own provider keys (BYOK) never counts against these windows.
Tiers
Your tier follows what you have bought. Settings > Rate limits shows your current tier and the exact figure for every window.
| Tier | How you get it |
|---|---|
| Free | Every new organization |
| Tier 1 | A credit purchase of $5 or more |
| Tier 2 | The Pro plan |
| Tier 3 | The Max plan |
| Tier 4 | The Ultra plan |
| Tier 5 | On request, from Settings > Rate limits |
A key can also carry its own requests and tokens per minute ceilings, set by an org admin under Budget & limits on the API keys page.
| At a glance | |
|---|---|
| Scope | Whole organization, all keys |
| Counted | Platform-funded traffic only |
| Not counted | Your own keys and plans (BYOK) |
| Daily reset | 00:00 UTC |
Windows and how they are counted
| Window | Counts | Error prefix |
|---|---|---|
| Requests per minute | Dispatches in a rolling 60 seconds | org_rate_limit |
| Tokens per minute | Settled tokens in a rolling 60 seconds | org_token_rate_limit |
| Tokens per hour | Settled tokens in a rolling hour | org_token_rate_limit_hour |
| Tokens per day | Settled tokens in the current UTC day | org_token_rate_limit_day |
Every dispatch counts, including one that later fails. A cached input token counts as at most a tenth of a token, so long cached prompts do not use up your token windows.
{
"error": {
"type": "rate_limit_error",
"code": "rate_limit_exceeded",
"message": "org_rate_limit: your organization reached its tier's requests per minute..."
}
}Retry-After: 12Which 429 is it
| Code | Whose limit | What to do |
|---|---|---|
rate_limit_exceeded | Your tier's window | Wait Retry-After, or move up a tier |
admission_capacity_exceeded | Too many of your requests waiting at once | Spread bursts out; a higher tier admits more at a time |
insufficient_quota | Credits or a spend cap, not a rate | Add credits or raise the cap. Retrying does not help |
free_limit_reached | A free allowance's window | Wait for the reset the message names |
The message always names your tier, the next tier's value for that window and the page that raises it. A provider's own throttle is handled by routing first and reaches you only when no other rung can take the request.
import time, openai
try:
reply = client.chat.completions.create(model="gpt-6-luna", messages=msgs)
except openai.RateLimitError as e:
time.sleep(int(e.response.headers.get("retry-after", "5")))Read your limits
A key can read its own effective ceilings. null means uncapped; source says whether a value was set on the key or comes from the default.
/api/gateway/keys/{api_key_id}/limitsThe figures in the example are illustrative. See Errors for every code.
curl https://api.experientiallabs.ai/api/gateway/keys/$API_KEY_ID/limits \
-H "Authorization: Bearer YOUR_API_KEY"{
"daily_spend_cap_nano_usd": null,
"spend_cap_period": "daily",
"requests_per_minute": 600,
"tokens_per_minute": 2000000,
"source": "default"
}