Rate limits
To mitigate against misuse and manage capacity on our API, we have implemented limits on how much an organization can use the Claude API.
We have two types of limits:
- Usage limits set a maximum monthly cost an organization can incur for API usage.
- Rate limits restrict the number of API requests an organization can make over a defined period of time.
About our limits
- Limits are designed to prevent API abuse, while minimizing impact on common customer usage patterns.
- Limits are defined by usage tier, where each tier is associated with a different set of usage and rate limits.
- Your organization will increase tiers automatically as you reach certain thresholds while using the API.
Limits are set at the organization level. You can see your organization’s limits in Plans and Billing in the Console. - You may hit rate limits over shorter time intervals. For instance, a rate of 60 requests per minute (RPM) may be enforced as 1 request per second. Short bursts of requests at a high volume can surpass the rate limit and result in rate limit errors.
- The limits outlined below are our standard limits and apply to the “Build” API plan. If you’re seeking higher, custom limits, contact sales by clicking “Select Plan” in the console to move to our custom “Scale” plan.
- All Claude models currently have the same usage and rate limits.
Usage limits
Each usage tier has a limit on how much you can use the API each calendar month. Once you reach the usage limit of your tier, until you qualify for the next tier, you will have to wait until the next month to be able to use the API again.
To qualify for the next tier, you must meet a deposit requirement and a mandatory wait period. Higher tiers require longer wait periods. Note, to minimize the risk of overfunding your account, you cannot deposit more than your monthly usage limit.
| Usage tier | Requirements to advance to tier | Max usage per month | |
|---|---|---|---|
| Credit purchase | Wait after first purchase | ||
| Free | N/A | 0 days | $10 |
| Build Tier 1 | $5 | 0 days | $100 |
| Build Tier 2 | $40 | 7 days | $500 |
| Build Tier 3 | $200 | 7 days | $1,000 |
| Build Tier 4 | $400 | 14 days | $5,000 |
| Scale | N/A | N/A | N/A |
Rate limits
Our rate limits are currently measured in requests per minute, tokens per minute, and tokens per day for each model class. If you exceed any of the rate limits you will get a 429 error. Click on the rate limit tier to view relevant rate limits.
| Model Tier | Requests per minute (RPM) | Tokens per minute (TPM) | Tokens per day (TPD) |
|---|---|---|---|
| Claude 3 Haiku | 5 | 25,000 | 300,000 |
| Claude 3 Sonnet | 5 | 20,000 | 300,000 |
| Claude 3 Opus | 5 | 10,000 | 300,000 |
Response Headers
The API response includes headers that show you the rate limit enforced, current usage, and when the limit will be reset.
The following headers are returned:
| Header | Description |
|---|---|
anthropic-ratelimit-requests-limit | The maximum number of requests allowed within the rate limit window. |
anthropic-ratelimit-requests-remaining | The number of requests remaining within the current rate limit window. |
anthropic-ratelimit-requests-reset | The time when the request rate limit window will reset, provided in RFC 3339 format. |
anthropic-ratelimit-tokens-limit | The maximum number of tokens allowed within the rate limit window. |
anthropic-ratelimit-tokens-remaining | The number of tokens remaining, rounded to the nearest thousand, within the current rate limit window. |
anthropic-ratelimit-tokens-reset | The time when the token rate limit window will reset, provided in RFC 3339 format. |
The tokens rate limit headers display the values for the limit (daily or per-minute) with fewer tokens remaining. For example, if you have exceeded the daily token limit but have not sent any tokens within the last minute, the headers will contain the daily token rate limit values.