Chutes AI
Researched 94d agoChutes AI
Chutes AI offers 5 tracked models (5 with output token pricing). This catalog covers coding, rag, and long context; open any model detail page for benchmarks, batch tiers, and migration prompts.
Covers 6 workload areas across 5 tracked models; last verified 2026-06-30.
Use it for
- Teams comparing token and batch pricing across this provider's models
- Operators routing coding, rag, and long context workloads through this API
Do not use it for
- Final benchmark picks without opening the relevant model detail page
Tracked models
5
Models available through this provider
Priced output routes
5
Models with output token pricing tracked
Cheapest output
$0.300
Gemma 2 9B Instruct on this route
Batch-ready models
0
No batch pricing tracked
Latest model release
2024-12-06
665d since newest release
Freshness
2026-06-30
Researched 94d ago
Information
Chutes AI is a decentralized GPU compute network providing inference API access to open-source AI models.
Links
X / TwitterWhere this host wins
- Coding: 1 tracked model with SWE-bench / HumanEval-style scores.
- RAG: 2 tracked models with ruler / needle retrieval benchmarks.
- Long-context: 2 tracked models with context-token or InfiniteBench-class signal.
- Vision: 1 tracked model with multimodal benchmark coverage.
Platform Overview
Chutes AI is a decentralized GPU compute network providing inference API access to open-source AI models.
Available Models(5)
View all →All models available as Serverless
| Model | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Grok-3 | $0.8 | $2.4 |
| Llama 3.3 70B Instruct (free) | $0.22 | $0.66 |
| Mistral Large 2 (2407) | $0.5 | $1.5 |
| Gemma 2 9B Instruct | $0.1 | $0.3 |
| Qwen2.5-72B-Instruct | $0.18 | $0.54 |