llm resource_error ai_generated true

openai.RateLimitError: You exceeded your current quota, please check your plan and billing details.

ID: llm/embeddings-api-quota-exceeded

Also available as: JSON · Markdown · 中文

85%Fix Rate

88%Confidence

1Evidence

2023-06-15First Seen

Version Compatibility

Version	Status	Introduced	Deprecated	Notes
openai>=1.0.0	active	—	—	—
openai==0.28.0	active	—	—	—

Root Cause

The API usage has exceeded the paid tier's token or request quota for the billing period, or the account has insufficient credits.

generic

中文

API使用量已超出当前付费层的令牌数或请求配额，或账户余额不足。

Official Documentation

https://platform.openai.com/docs/guides/error-codes/api-errors

Workarounds

90% success Check billing dashboard at https://platform.openai.com/account/billing and add funds or upgrade plan. Then monitor usage via API: import openai usage = openai.Usage.retrieve() print(usage)
```
Check billing dashboard at https://platform.openai.com/account/billing and add funds or upgrade plan. Then monitor usage via API:
import openai
usage = openai.Usage.retrieve()
print(usage)
```
80% success Implement a fallback to a different embedding model or provider when quota is exceeded: if 'quota' in str(e): model = 'text-embedding-ada-002' # Fallback to cheaper model response = openai.Embedding.create(input=text, model=model)
```
Implement a fallback to a different embedding model or provider when quota is exceeded:
if 'quota' in str(e):
    model = 'text-embedding-ada-002'  # Fallback to cheaper model
    response = openai.Embedding.create(input=text, model=model)
```

中文步骤

在https://platform.openai.com/account/billing检查账单仪表板并添加资金或升级套餐。然后通过API监控使用量：
import openai
usage = openai.Usage.retrieve()
print(usage)

当超出配额时，实现回退到不同的嵌入模型或提供商：
if 'quota' in str(e):
    model = 'text-embedding-ada-002'  # 回退到更便宜的模型
    response = openai.Embedding.create(input=text, model=model)

Dead Ends

Common approaches that don't work:

70% fail
The error is a quota exhaustion, not a rate limit. Retrying will keep failing until the billing period resets or more credits are added.
50% fail
The quota is based on total usage, not request size. Reducing batch size doesn't help if the total quota is exhausted.