Free models and APIs on Groq in 2026
Groq focuses on exceptionally fast inference and offers a useful free tier for supported open models.
4 modelsup to 262K contextbest: Qwen 3.8 27BUpdated:
Groq
Online at the last check
Free plan with per-model limits on requests and tokens per minute and per day; very high generation speed on LPU hardware.
- Base URL
https://api.groq.com/openai/v1- Compatibility
- OpenAI Chat Completions
- Card
- Not required
- Limits
- 14,400 req/day · 30 req/min · 6,000 tokens/min
| # | Model ↕ | AA Index ↕ | Context ↕ | Size ↕ | Limit | |
|---|---|---|---|---|---|---|
| 1 | 
Qwen 3.8 27B
qwen/qwen3.8-27b |
33.7 | 131K | Mid-size | 14,400 req/day | Open |
| 2 | 
gpt-oss-20b
openai/gpt-oss-20b |
10.0 | 131K | Mid-size | 14,400 req/day | Open |
| 3 |
gpt-oss-120b
openai/gpt-oss-120b |
11.6 | 131K | Frontier | 14,400 req/day | Open |
| 4 |
Allam 2 7B
allam-2-7b |
— | 4K | Small | 14,400 req/day | Open |
No models match your filters.
Benchmarks: Artificial Analysis (October 24, 2026). A dash means the model is not on their leaderboard; we never estimate scores ourselves.
FAQ
Is Groq free?
Free plan with per-model limits on requests and tokens per minute and per day; very high generation speed on LPU hardware. 4 models are currently free.
Is Groq compatible with the OpenAI API?
Yes — use the base URL https://api.groq.com/openai/v1 with any OpenAI-compatible client or SDK.
Does Groq require a card?
No, free models work without a card.