GR
Groq
Groq
High-speed LPU inference for open-source models with predictable per-token pricing.
Plans
Llama 3.1 8B on Groq
Free / usage_based
- LPU high-speed inference
- OpenAI-compatible API
- Free tier available
Llama 3.3 70B on Groq
Free / usage_based
- LPU high-speed inference
- OpenAI-compatible API
- Free tier available
GPT OSS Safeguard 20B on Groq
Free / usage_based
- LPU high-speed inference
- OpenAI-compatible API
- Free tier available
GPT OSS 20B on Groq
Free / usage_based
- LPU high-speed inference
- OpenAI-compatible API
- Free tier available
Qwen3 32B on Groq
Free / usage_based
- LPU high-speed inference
- OpenAI-compatible API
- Free tier available
Llama 3.3 70B on Groq
Free / usage_based
- LPU high-speed inference
- OpenAI-compatible API
- Free tier available
Llama 3.1 8B on Groq
Free / usage_based
- LPU high-speed inference
- OpenAI-compatible API
- Free tier available
Qwen 3.6 27B on Groq
Free / usage_based
- LPU high-speed inference
- OpenAI-compatible API
- Free tier available
GPT OSS 120B on Groq
Free / usage_based
- LPU high-speed inference
- OpenAI-compatible API
- Free tier available
Llama 4 Scout on Groq
Free / usage_based
- LPU high-speed inference
- OpenAI-compatible API
- Free tier available