Groq
Inference cloud
- Catalog status
- List checked 24m ago
- Last successful check
- 2026-11-20 (24m ago)
- Latest attempt
- 24m ago: succeeded
"List checked" means we fetched the provider's model list in the last 3 hours. That shows the list is reachable and current, not that inference works.
Free quota
Free
Free tier
- Kind
- Recurring
- Credit
- Not documented
- Tokens granted
- Not documented
- Expires after
- Not documented
- Renews every
- Not documented
- Card required
- Not documented
- Phone required
- Not documented
- Trains on prompts
- No
- Commercial use
- Yes
- Eligibility
- 18 or older
- Note
- Limits shown are the Free Plan values for the three recorded models, which are identical. Other free models differ, e.g. openai/gpt-oss-safeguard-20b has 3 RPM and 2K TPM. Applied per organization, not per user or key. Some organizations also have separate per-minute input and output token caps. Cached tokens do not count towards limits.
- Source
- Provider page, checked 2026-11-01
| Limits | Per minute | Per day | Per month |
|---|---|---|---|
| Requests | 30 | 1,000 | Not documented |
| Tokens | 8,000 | 200,000 | Not documented |
Models covered
openai/gpt-oss-120bopenai/gpt-oss-20bqwen/qwen3.8-27b
How to call it
- OpenAI-compatible
- Yes, Chat Completions at the base URL
- Base URL
https://api.groq.com/openai/v1
curl "https://api.groq.com/openai/v1/chat/completions" \
-H "Authorization: Bearer $GROQ_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "allam-2-7b", "messages": [{"role": "user", "content": "Hello"}]}'
Models
| Model ID | Comparison key | Input $/1M | Output $/1M | Price checked |
|---|---|---|---|---|
allam-2-7b |
sdaia/allam-2-7b |
$0 | $0 | models.dev, synced 13h ago |
canopylabs/orpheus-arabic-saudi |
canopylabs/orpheus-arabic-saudi |
unknown | unknown | — |
canopylabs/orpheus-v1-english |
canopylabs/orpheus-v1-english |
unknown | unknown | — |
meta-llama/llama-prompt-guard-2-22m |
meta/llama-prompt-guard-2-22m |
$0.03 | $0.03 | models.dev, synced 13h ago |
meta-llama/llama-prompt-guard-2-86m |
meta/llama-prompt-guard-2-86m |
$0.04 | $0.04 | models.dev, synced 13h ago |
openai/gpt-oss-120b |
openai/gpt-oss-120b |
$0.15 | $0.6 | models.dev, synced 13h ago |
openai/gpt-oss-20b |
openai/gpt-oss-20b |
$0.075 | $0.3 | models.dev, synced 13h ago |
openai/gpt-oss-safeguard-20b |
openai/gpt-oss-safeguard-20b |
$0.075 | $0.3 | models.dev, synced 13h ago |
qwen/qwen3.8-27b |
alibaba/qwen3.8-27b |
$0.8 | $4 | models.dev, synced 13h ago |
whisper-large-v3 |
openai/whisper-large-v3 |
unknown | unknown | — |
whisper-large-v3-turbo |
openai/whisper-large-v3-turbo |
unknown | unknown | — |