Provider model catalog

Groq models

Ultra-fast inference on custom LPU hardware

14 unique catalog models

Model pricing and capabilities

• gemma-7b-it$0.050 / 1M tokens input
• llama-3.1-8b-instant$0.050 / 1M tokens input
• llama-3.3-70b-versatile$0.590 / 1M tokens input
• llama-4-maverick-17b-128e-instruct$0.200 / 1M tokens input
• llama-4-scout-17b-16e-instruct$0.110 / 1M tokens input
• llama-guard-4-12b$0.200 / 1M tokens input
• kimi-k2-instruct-0905$1.00 / 1M tokens input
• gpt-oss-120b$0.150 / 1M tokens input
• gpt-oss-20b$0.075 / 1M tokens input
• gpt-oss-safeguard-20b$0.075 / 1M tokens input
• playai-ttsNot listed input
• qwen3-32b$0.290 / 1M tokens input
• whisper-large-v3Not listed input
• whisper-large-v3-turboNot listed input