All Providers
16Models
6Families
131.1KMax Context
$0–$0.80Input Cost/MTok
$0–$4Output Cost/MTok
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Setup
Set the following environment variable to use Groq:
GROQ_API_KEYModels (16)
| Model | Model ID | Input Cost | Output Cost | Context | Capabilities |
|---|---|---|---|---|---|
| ALLaM 2.7b | allam-2-7b | $0/MTok | $0/MTok | 4.1K | Open |
| Llama Prompt Guard 2 22Mllama | meta-llama/llama-prompt-guard-2-22m | $0.03/MTok | $0.03/MTok | 512 | Open |
| Prompt Guard 2 86Mllama | meta-llama/llama-prompt-guard-2-86m | $0.04/MTok | $0.04/MTok | 512 | Open |
| Llama 3.1 8Bllama | llama-3.1-8b-instant | $0.05/MTok | $0.08/MTok | 131.1K | ToolsOpen |
| GPT OSS 20Bgpt-oss | openai/gpt-oss-20b | $0.07/MTok | $0.30/MTok | 131.1K | ReasoningToolsOpen |
| Safety GPT OSS 20Bgpt-oss | openai/gpt-oss-safeguard-20b | $0.07/MTok | $0.30/MTok | 131.1K | ReasoningToolsOpen |
| GPT OSS 120Bgpt-oss | openai/gpt-oss-120b | $0.15/MTok | $0.60/MTok | 131.1K | ReasoningToolsOpen |
| Llama 3.3 70Bllama | llama-3.3-70b-versatile | $0.59/MTok | $0.79/MTok | 131.1K | ToolsOpen |
| Qwen 3.6 27Bqwen | qwen/qwen3.6-27b | $0.60/MTok | $3/MTok | 131.1K | ReasoningToolsOpen |
| Qwen 3.8 27Bqwen | qwen/qwen3.8-27b | $0.80/MTok | $4/MTok | 131.0K | ReasoningToolsOpen |
| Whisperwhisper | whisper-large-v3 | —/MTok | —/MTok | — | Open |
| Whisper Large V3 Turbowhisper | whisper-large-v3-turbo | —/MTok | —/MTok | — | Open |
| Compoundgroq | groq/compound | —/MTok | —/MTok | 131.1K | |
| Compound Minigroq | groq/compound-mini | —/MTok | —/MTok | 131.1K | |
| Canopy Labs Orpheus V1 Englishcanopylabs | canopylabs/orpheus-v1-english | —/MTok | —/MTok | 4K | |
| Canopy Labs Orpheus Arabic Saudicanopylabs | canopylabs/orpheus-arabic-saudi | —/MTok | —/MTok | 4K |