Model catalogue
Groq model prices, context windows and capabilities
16 Groq models with list prices per million tokens, context windows and capabilities. The lowest input price is $0.03 per million tokens, for Llama Prompt Guard 2 22M. The largest context window is 131K tokens, on Compound. In the DVARA LLM Gateway, these models are reached through the groq provider.
- 2 with vision
- 7 with tool calling
- 5 with structured output
- 5 with reasoning
- Snapshot
16 models
| Capabilities | ||||||
|---|---|---|---|---|---|---|
ALLaM-2-7bgroq/allam-2-7b | $0 | $0 | — | 4K | 4K |
|
Canopy Labs Orpheus Arabic Saudigroq/canopylabs/orpheus-arabic-saudi | — | — | — | 4K | 50K |
|
Canopy Labs Orpheus V1 Englishgroq/canopylabs/orpheus-v1-english | — | — | — | 4K | 50K |
|
Compoundgroq/groq/compound | — | — | — | 131K | 8K |
|
Compound Minigroq/groq/compound-mini | — | — | — | 131K | 8K |
|
GPT OSS 120Bgroq/openai/gpt-oss-120b | $0.15 | $0.6 | $0.075 | 131K | 66K |
|
GPT OSS 20Bgroq/openai/gpt-oss-20b | $0.075 | $0.3 | $0.0375 | 131K | 66K |
|
Llama 3.1 8Bgroq/llama-3.1-8b-instant | $0.05 | $0.08 | — | 131K | 131K |
|
Llama 3.3 70Bgroq/llama-3.3-70b-versatile | $0.59 | $0.79 | — | 131K | 33K |
|
Llama Prompt Guard 2 22Mgroq/meta-llama/llama-prompt-guard-2-22m | $0.03 | $0.03 | — | 512 | 512 |
|
Prompt Guard 2 86Mgroq/meta-llama/llama-prompt-guard-2-86m | $0.04 | $0.04 | — | 512 | 512 |
|
Qwen3.6 27Bgroq/qwen/qwen3.6-27b | $0.6 | $3 | $0.3 | 131K | 16K |
|
Qwen3.8 27Bgroq/qwen/qwen3.8-27b | $0.8 | $4 | — | 131K | 16K |
|
Safety GPT OSS 20Bgroq/openai/gpt-oss-safeguard-20b | $0.075 | $0.3 | — | 131K | 66K |
|
Whispergroq/whisper-large-v3 | — | — | — | — | — |
|
Whisper Large V3 Turbogroq/whisper-large-v3-turbo | — | — | — | — | — |
|