Groq
15 modelsGroq serves open-weight models on custom LPU hardware for extremely fast inference. This page lists every model Groq exposes in the directory - Llama, Qwen, Whisper, and more - with per-million-token pricing, context window sizes, output limits, and features like tool calling and structured output.
groq.comAPI base: https://api.groq.com/openai/v1
15 of 15 modelsShowing 15 of 15 models from 1 provider
ALLaM-2-7b allam-2-7b | - | - | - | - | - | - | - | 4.1K | - | 4.1K | Structured output | Text | Text | Jan 23, 2025 | - | - | - | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 | |
Canopy Labs Orpheus Arabic Saudi canopylabs/orpheus-arabic-saudi | - | - | - | - | - | - | - | 4K | - | 50K | - | Text | Audio | Dec 16, 2025 | - | - | - | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 | |
Canopy Labs Orpheus V1 English canopylabs/orpheus-v1-english | - | - | - | - | - | - | - | 4K | - | 50K | - | Text | Audio | Dec 19, 2025 | - | - | - | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 | |
GPT OSS 20B openai/gpt-oss-20b | $0.075 | $0.3 | - | $0.037 | - | - | - | 131.1K | - | 65.5K | ReasoningToolsStructured outputOpen weights | Text | Text | Aug 5, 2025 | - | - | Yes | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 | |
GPT OSS 120B openai/gpt-oss-120b | $0.15 | $0.6 | - | $0.075 | - | - | - | 131.1K | - | 65.5K | ReasoningToolsStructured outputOpen weights | Text | Text | Aug 5, 2025 | - | - | Yes | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 | |
Llama 3.1 8B llama-3.1-8b-instant | - | - | - | - | - | - | - | 131.1K | - | 131.1K | ToolsStructured output | Text | Text | - | - | - | - | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 | |
Llama 3.3 70B llama-3.3-70b-versatile | - | - | - | - | - | - | - | 131.1K | - | 32.8K | ToolsStructured output | Text | Text | - | - | - | - | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 | |
Llama Prompt Guard 2 22M meta-llama/llama-prompt-guard-2-22m | $0.03 | $0.03 | - | - | - | - | - | 512 | - | 512 | - | Text | Text | May 30, 2025 | - | - | - | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 | |
MiniMax M2.7 minimaxai/minimax-m2.7 | - | - | - | - | - | - | - | 196.6K | - | 131.1K | ReasoningToolsStructured outputTemperature | Text | Text | - | - | - | - | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 | |
Muse Spark Open meta-models/muse-spark-open | - | - | - | - | - | - | - | 131.1K | - | 131.1K | ReasoningToolsStructured outputFilesOpen weights | ImageText | Text | - | - | - | Yes | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 | |
Prompt Guard 2 86M meta-llama/llama-prompt-guard-2-86m | $0.04 | $0.04 | - | - | - | - | - | 512 | - | 512 | Structured output | Text | Text | May 30, 2025 | - | - | - | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 | |
Qwen/Qwen3.8-27B qwen/qwen3.8-27b | $0.8 | $4 | - | - | - | - | - | 131.1K | - | 16.4K | ReasoningToolsStructured outputFilesTemperature | ImageText | Text | Aug 17, 2026 | - | - | - | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 | |
Safety GPT OSS 20B openai/gpt-oss-safeguard-20b | $0.075 | $0.3 | - | $0.037 | - | - | - | 131.1K | - | 65.5K | ReasoningToolsStructured output | Text | Text | Oct 29, 2025 | - | - | - | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 | |
Whisper whisper-large-v3 | - | - | - | - | - | - | - | 448 | - | 448 | Files | Audio | Text | Sep 3, 2023 | - | - | - | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 | |
Whisper Large V3 Turbo whisper-large-v3-turbo | - | - | - | - | - | - | - | 448 | - | 448 | Files | Audio | Text | Oct 8, 2024 | - | - | - | @ai-sdk/groq | GROQ_API_KEY | https://api.groq.com/openai/v1 |