Groq
Groq is the premier neocloud for fast inference. One fully integrated platform for infrastructure, inference, and control. Millions of developers run trillions of tokens on Groq every week. Inference platform · OpenAI-compatible API · Fast Inference · Low Latency · Lpu · Open Weight
Intelligence vs Price
Best value among Groq models on this chart: GPT OSS 120B · GPT OSS 20B · Llama 3.1 8B Instruct. Prices use each model's lowest available Groq price across regions. Hover any dot for full pricing, or click a creator in the legend to isolate.
Groq models
14 models in Global, 11 with pricingModel | Creator | Input Price, $ | Output Price, $ | Context | Max Output | Inference Providers | Intelligence | Coding | |
|---|---|---|---|---|---|---|---|---|---|
| GPT OSS 120B | 0.15 | 0.6 | 131K | 131K | compare (24) | 24.1#1 | 30.4#1 | ||
| GPT OSS 20B | 0.075 | 0.3 | 131K | 131K | compare (18) | 15.2#2 | 20.7#2 | ||
| Llama 3.3 70B Instruct | 0.59 | 0.79 | 131K | 120K | compare (21) | 9.3#3 | 11.9#3 | ||
| Llama 3.1 8B Instruct | 0.05 | 0.08 | 200K | 128K | compare (20) | 7.4#4 | 5.4#4 | ||
| Gemma 7B IT | 0.05 | 0.08 | 8K | 8K | compare (3) | N/A | N/A | ||
| GPT OSS 20B Safeguard | 0.075 | 0.3 | 131K | 66K | compare (5) | N/A | N/A | ||
| Kimi K2 Instruct | 1.00 | 3.00 | 262K | 33K | compare (9) | N/A | N/A | ||
| Llama 4 17B Maverick Instruct | 0.2 | 0.6 | 1.0M | 16K | compare (9) | N/A | N/A | ||
| Llama 4 17B Scout Instruct | 0.11 | 0.34 | 10.0M | 16K | compare (12) | N/A | N/A | ||
| LlamaGuard 4 12B | 0.2 | 0.2 | 1.0M | 16K | compare (4) | N/A | N/A | ||
| PlayAI TTS | N/A | N/A | 10K | 10K | compare (1) | N/A | N/A | ||
| Qwen3 32B | 0.29 | 0.59 | 131K | 41K | compare (15) | N/A | N/A | ||
| Whisper 3 Large | N/A | N/A | N/A | N/A | compare (1) | N/A | N/A | ||
| Whisper 3 Large Turbo | N/A | N/A | N/A | N/A | compare (3) | N/A | N/A |