> ## Documentation Index
> Fetch the complete documentation index at: https://docs-preprod.sambanova.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Rate limits
Rate limits are a mechanism to help manage SambaNova API usage to provide stable performance and reliable service. They limit how many times each user can call the SambaNova API within a given interval.
Rate limits are measured in:
* RPM: Requests per minute
* RPD: Requests per day
Basics
* A **request** is defined by a call to our API
* You can hit either limit type (RPM or RPD) depending on which one you reach first
* You will be notified in every request response what the status of your rate limits are ([see rate limit response headers for more information](#rate-limit-response-headers))
* If you hit a rate limit, you will be sent an error message in your response ([see API error codes](https://docs.sambanova.ai/cloud/api-reference/using-the-api/api-error-codes))
## SambaStack rate limits
For SambaStack deployments, rate limits are optional and applied to user groups by the administrator.
## SambaCloud rate limit tiers
There are a few different rate limit tier offerings we provide:
* **Free Tier**: Applied when there is no payment method linked with your account
* **Developer Tier**: Applied when a payment method is linked with your account
* **Enterprise Tier**: Please [contact our sales team](https://sambanova.ai/contact) for our enterprise tier rate limit plans
Please see the [Billing page](https://cloud.sambanova.ai/plans/billing) to link a payment method to your account.
Below are our Developer Tier and Free Tier rate limits.
### Production model rate limits
Production models are intended for use in production environments and meet our high standards for speed and quality.
| **Developer** | **Model ID** | **Requests per minute** (RPM) | **Requests per day** (RPD) |
| :------------ | :------------------------------ | :---------------------------- | :------------------------- |
| **DeepSeek** | | | |
| | `DeepSeek-R1` | 60 | 12000 |
| | `DeepSeek-R1-Distill-Llama-70B` | 240 | 48000 |
| | `DeepSeek-V3-0324` | 60 | 12000 |
| | `Deepseek-V3.1` | 60 | 12000 |
| **Meta** | | | |
| | `Meta-Llama-3.3-70B-Instruct` | 240 | 48000 |
| | `Meta-Llama-3.1-8B-Instruct` | 1440 | 288000 |
| **Developer** | **Model ID** | **Requests per minute** (RPM) | **Requests per day** (RPD) |
| :------------ | :------------------------------ | :---------------------------- | :------------------------- |
| **DeepSeek** | | | |
| | `DeepSeek-R1` | 20 | 400 |
| | `DeepSeek-R1-Distill-Llama-70B` | 80 | 1600 |
| | `DeepSeek-V3-0324` | 20 | 400 |
| | `Deepseek-V3.1` | 20 | 400 |
| **Meta** | | | |
| | `Meta-Llama-3.3-70B-Instruct` | 80 | 1600 |
| | `Meta-Llama-3.1-8B-Instruct` | 480 | 9600 |
### Preview model rate limits
Preview models are intended for evaluation purposes and developer experimentation only, and should not be used in production environments. These models have limited capacity and may be removed at short notice.
| **Developer** | **Model ID** | **Requests per minute** (RPM) | **Requests per day** (RPD) |
| :---------------- | :------------------------------------ | :---------------------------- | :------------------------- |
| **Meta** | | | |
| | `Llama-4-Maverick-17B-128E-Instruct` | 60 | 12000 |
| **OpenAI** | | | |
| | `Whisper-Large-v3` | 450 | 90000 |
| **Qwen** | | | |
| | `Qwen3-32B` | 30 | 6000 |
| **Tokyotech-llm** | | | |
| | `Llama-3.3-Swallow-70B-Instruct-v0.4` | 60 | 12000 |
| **Other** | | | |
| | `E5-Mistral-7B-Instruct` | 60 | 12000 |
| **Developer** | **Model ID** | **Requests per minute** (RPM) | **Requests per day** (RPD) |
| :---------------- | :------------------------------------ | :---------------------------- | :------------------------- |
| **Meta** | | | |
| | `Llama-4-Maverick-17B-128E-Instruct` | 20 | 400 |
| **OpenAI** | | | |
| | `Whisper-Large-v3` | 150 | 3000 |
| **Qwen** | | | |
| | `Qwen3-32B` | 10 | 200 |
| **Tokyotech-llm** | | | |
| | `Llama-3.3-Swallow-70B-Instruct-v0.4` | 20 | 400 |
| **Other** | | | |
| | `E5-Mistral-7B-Instruct` | 20 | 400 |
## Rate limit response headers
These headers are found in every request response and give information about the current status of rate limit usage.
**RPM (Requests per minute):**
* `x-ratelimit-limit-requests`
* The maximum number of requests allowed per minute.
* `x-ratelimit-remaining-requests`
* The number of requests remaining in the current minute before hitting the rate limit.
* `x-ratelimit-reset-requests`
* Time in epoch time until the per-minute request quota resets.
**RPD (Requests per day):**
* `x-ratelimit-limit-requests-day`
* The maximum number of requests allowed per day.
* `x-ratelimit-remaining-requests-day`
* The number of requests remaining in the current day before hitting the rate limit.
* `x-ratelimit-reset-requests-day`
* Time in epoch time until the per-day request quota resets.