Chutes AI Models — Pricing & Benchmarks
5 models available
Last refreshed 2026-06-30. Next refresh: weekly.
Chutes AI hosts 5 AI models in this catalog. The lowest listed input price is Gemma 2 9B Instruct at $0.1/1M input tokens. LLM Reference compares these models across all 97 providers.
| Model | Input (per 1M) | Output (per 1M) | Context | |
|---|---|---|---|---|
| Gemma 2 9B Instruct | $0.1 | $0.3 | 8k | |
| Qwen2.5-72B-Instruct | $0.18 | $0.54 | 128k | |
| Llama 3.3 70B Instruct (free) | $0.22 | $0.66 | 66k | |
| Mistral Large 2 (2407) | $0.5 | $1.50 | 128k | |
| Grok-3 | $0.8 | $2.40 | 131k |
Where else to run this
Mistral Large 2 (2407) on Chutes AI
Provider setup and pricing
Gemma 2 9B Instruct on Chutes AI
Provider setup and pricing
Qwen2.5-72B-Instruct on Chutes AI
Provider setup and pricing
Mistral Large 2 (2407) on Microsoft Foundry
Alternative host
Gemma 2 9B Instruct on Fireworks AI
Alternative host
Qwen2.5-72B-Instruct on DeepInfra
Alternative host
Pricing Overview
Cheapest$0.10/1M
Most expensive$0.80/1M