Free tier - verified
Is the Groq API free?
Yes. The Groq API offers a standing Free tier until you upgrade to the Developer tier. Whether a card is required is not stated. Trains on your data: No (Services Agreement covers all Cloud Services).
Read from console.groq.com. Compare every free LLM API
- Offer
- Free tier
- Card required
- Not stated
- Trains on data
- No
- Verified
- 2026-10-18
The offer
- Offer class
Standing free tier
- How to get it
Sign up at console.groq.com and create an API key; accounts are on the Free tier until upgraded to the Developer tier.
“To upgrade from the Free tier to the Developer tier, you'll need to provide a valid payment method (credit card, US bank account, or SEPA debit account).”
console.groq.com - Card required
Not stated
Not stated explicitly for the Free tier; Groq documents a payment method only as a requirement for upgrading to the Developer tier (quote above).
Free-tier limits
Values are copied exactly as the provider publishes them, units included. Not stated means the public docs give no value.
| Model | RPM | RPD | TPM | TPD | ASH | ASD |
|---|---|---|---|---|---|---|
| openai/gpt-oss-120b | 30 | 1K | 8K | 200K | - | - |
| openai/gpt-oss-20b | 30 | 1K | 8K | 200K | - | - |
| qwen/qwen3.8-27b | 30 | 1K | 8K | 200K | - | - |
| openai/gpt-oss-safeguard-20b | 3 | 1K | 2K | 200K | - | - |
| meta-llama/llama-prompt-guard-2-22m | 30 | 14.4K | 15K | 500K | - | - |
| meta-llama/llama-prompt-guard-2-86m | 30 | 14.4K | 15K | 500K | - | - |
| whisper-large-v3 | 20 | 2K | - | - | 7.2K | 28.8K |
| whisper-large-v3-turbo | 20 | 2K | - | - | 7.2K | 28.8K |
| canopylabs/orpheus-v1-english | 10 | 100 | 1.2K | 3.6K | - | - |
| canopylabs/orpheus-arabic-saudi | 10 | 100 | 1.2K | 3.6K | - | - |
All 10 rows of the 'Free Plan Limits' tab on the rate-limits page (includes speech-to-text, text-to-speech and prompt-guard models). Units as published: RPM requests per minute, RPD requests per day, TPM tokens per minute, TPD tokens per day, ASH audio seconds per hour, ASD audio seconds per day. The page calls the table 'a high level summary and there may be exceptions to these limits'; exact per-org values are on the logged-in Limits page.
From the limits docs
“Rate limits apply at the organization level, not individual users. You can hit any limit type depending on which threshold you reach first.”
“Free Plan Limits | Developer Plan Limits | MODEL ID | RPM | RPD | TPM | TPD | ASH | ASD | ... openai/gpt-oss-120b | 30 | 1K | 8K | 200K | - | -”
“The following is a high level summary and there may be exceptions to these limits. You can view the current, exact rate limits for your organization on the limits page in your account settings.”
“Note that the limits shown below are the base limits for the Developer plan, and higher limits are available for select workloads and enterprise use cases.”
- Cached tokens do not count towards your rate limits.
- some organizations are also subject to separate per-minute limits on input tokens (ITPM) and output tokens (OTPM)
Does it train on your data?
No
Services Agreement covers all Cloud Services
No. The Services Agreement says Groq is not permitted to use Inputs or Outputs for training unless the customer explicitly permits it; inference data is not retained by default (up to 30 days only for reliability/abuse investigation; Zero Data Retention available to all customers). Not stated separately for the Free tier: the agreement covers all Cloud Services.
“For clarity, Groq is not permitted to use Inputs or Outputs for training or fine-tuning any AI Model Services or other models, unless explicitly granted permission or instructed by Customer.”
“By default, Groq does not retain customer data for inference requests.”
“These logs are retained for up to 30 days, unless legally required to retain longer.”
“All customers may enable Zero Data Retention (ZDR) in Data Controls settings.”
“Except as otherwise expressly indicated in Documentation, Groq's DPA and BAA do not apply to Beta Services.”
Terms last modified June 22, 2026.
Also read: https://console.groq.com/docs/your-data
Restrictions
Use
“Cloud Services and the AI Model Services under this Agreement are not for consumer use.”
console.groq.com Liability on free services
“GROQ'S TOTAL AGGREGATE LIABILITY FOR DAMAGES ARISING OUT OF OR RELATED TO BETA SERVICES AND ANY CLOUD SERVICES PROVIDED FREE OF CHARGE IS LIMITED TO $5,000.”
console.groq.com Data location
“All customer data is retained in Google Cloud Platform (GCP) buckets located in the United States.”
console.groq.com
Upgrade path
Add a payment method to move to the pay-as-you-go Developer tier: higher limits (e.g. openai/gpt-oss-120b 1K RPM, 500K RPD, 250K TPM, no TPD shown), Batch and Flex processing, spend limits and chat support; no immediate charge.
“When you upgrade, there's no immediate charge - you'll be billed for tokens at month-end or when you reach progressive billing thresholds”
“Need higher rate limits? Upgrade to Developer plan to access higher limits, Batch and Flex processing, and more.”
Developer plan limits (paid), for comparison
From the 'Developer Plan Limits' tab (devRows in the page data). Columns RPM, RPD, TPM, TPD, ASH, ASD.
| Model | RPM | RPD | TPM | TPD | ASH | ASD |
|---|---|---|---|---|---|---|
| openai/gpt-oss-120b | 1K | 500K | 250K | - | - | - |
| openai/gpt-oss-20b | 1K | 500K | 250K | - | - | - |
| qwen/qwen3.8-27b | 1K | 500K | 250K | - | - | - |
| openai/gpt-oss-safeguard-20b | 1K | 500K | 150K | - | - | - |
| meta-llama/llama-prompt-guard-2-22m | 100 | 50K | 30K | - | - | - |
| meta-llama/llama-prompt-guard-2-86m | 100 | 50K | 30K | - | - | - |
| whisper-large-v3 | 300 | 200K | - | - | 200K | 4M |
| whisper-large-v3-turbo | 400 | 200K | - | - | 400K | 4M |
| canopylabs/orpheus-v1-english | 250 | 100K | 50K | - | - | - |
| canopylabs/orpheus-arabic-saudi | 250 | 100K | 50K | - | - | - |
FAQ
Is the Groq API free?
Yes. The Groq API offers a standing Free tier until you upgrade to the Developer tier. Whether a card is required is not stated. Trains on your data: No (Services Agreement covers all Cloud Services).
What are the Groq free limits?
openai/gpt-oss-120b: 30 RPM, 1K RPD, 8K TPM, 200K TPD. All 10 rows of the 'Free Plan Limits' tab on the rate-limits page (includes speech-to-text, text-to-speech and prompt-guard models). Units as published: RPM requests per minute, RPD requests per day, TPM tokens per minute, TPD tokens per day, ASH audio seconds per hour, ASD audio seconds per day. The page calls the table 'a high level summary and there may be exceptions to these limits'; exact per-org values are on the logged-in Limits page.
Does Groq train on your data?
No (Services Agreement covers all Cloud Services). The terms say: "For clarity, Groq is not permitted to use Inputs or Outputs for training or fine-tuning any AI Model Services or other models, unless explicitly granted permission or instructed by Customer."
Sources
Last verified from Groq's own pages below. Quotes are verbatim.
Newsletter
Know when a free tier changes
One email per week. New model releases, pricing and limit changes, and what they mean for what you build.