Models on GroqCloud
9 models available · Groq
| Model | Input (per 1M) | Output (per 1M) | Context | |
|---|---|---|---|---|
| Llama Prompt Guard 2 22M | $0.03 | $0.03 | 512 | |
| Llama Prompt Guard 2 86M | $0.04 | $0.04 | 512 | |
| Llama 3.1 8B Instruct | $0.05 | $0.08 | 128K | |
| GPT OSS Safeguard 20B | $0.075 | $0.30 | 131072 | |
| gpt-oss-20b | $0.075 | $0.30 | 131072 | |
| Llama 4 Scout 17B-16E Instruct | $0.11 | $0.34 | 328K | |
| gpt-oss-120b | $0.15 | $0.60 | 131072 | |
| Qwen3 32B | $0.29 | $0.59 | 40K | |
| Llama 3.3 70B Instruct (free) | $0.59 | $0.79 | 66K |
Pricing Overview
About GroqCloud
Groq's AI platform is built around its groundbreaking Language Processing Unit (LPU™), an innovative architecture designed for high-speed AI inference tasks. The LPU™ delivers exceptional performance, achieving speeds up to 1000 times faster than traditional models like ChatGPT, with remarkably low latency. This makes it ideal for real-time applications such as chatbots and voice assistants. The platform is versatile, capable of handling various AI workloads including natural language processing, computer vision, and complex computations without extensive retraining or reconfiguration. It supports mixed-precision operations and comes with a user-friendly software stack, simplifying deployment and enhancing the overall user experience. The platform is further enhanced by GroqChat and the GroqCloud™ Developer Hub, which provide developers with powerful AI tools and resources. GroqChat enables seamless interaction with multiple large language models (LLMs), while the GroqCloud™ Developer Hub offers a no-code environment for exploring APIs and featured models. This allows for rapid development and experimentation without requiring extensive coding knowledge. The platform's on-demand pricing and flexible deployment options make it adaptable to diverse enterprise needs, facilitating quick integration of AI capabilities into various operational workflows and enhancing productivity and efficiency.
Full provider profile →