Groq
Model AggregatorModels
13
Prompt Caching
✓
Batch Discount
—
Tool Calling
✓
Model13
| Model | Input Price | Output Price | Cached Input | Context | Modality |
|---|---|---|---|---|---|
| Canopy Labs Orpheus Arabic SaudiOrpheus | $40/1M chars | — | — | — | audio |
| Canopy Labs Orpheus EnglishOrpheus | $22/1M chars | — | — | — | audio |
| GPT OSS 120BGPT-OSS | $0.15 | $0.6 | $0.075 | 128K | text |
| GPT OSS 20BGPT-OSS | $0.075 | $0.3 | $0.0375 | 128K | text |
| GPT OSS Safeguard 20BGPT-OSS | $0.075 | $0.3 | — | — | text |
| kimi-k2-instruct-0905Kimi | $1 | $3 | $0.5 | — | text |
| Llama 3.1 8B InstantLlama | $0.05 | $0.08 | — | 128K | text |
| Llama 3.3 70B VersatileLlama | $0.59 | $0.79 | — | 128K | text |
| Llama 4 Scout (17Bx16E)Llama | $0.11 | $0.34 | — | 128K | text |
| Qwen3 32BQwen | $0.29 | $0.59 | — | 131K | text |
| Qwen 3.6 27BQwen | $0.6 | $3 | — | 131K | text |
| Whisper Large v3 TurboWhisper | $0.000667/min | — | — | — | audio |
| Whisper V3 LargeWhisper | $0.00185/min | — | — | — | audio |