Chutes API pricing
8 Chutes models. Source: https://llm.chutes.ai/v1/models
- Provider type
- Inference host
- Server location (where inference runs)
- unknown
- Regions
- unknown
- Company HQ (secondary)
- unknown (unknown) · Operated by Chutes Global Corp; Terms governed by the laws of Nevis, Saint Kitts and Nevis (chutes.ai/terms). OpenRouter's provider list says US.
- EU data residency
- unknown
- Residency notes
- Terms: Chutes is a decentralized AI inference platform running on distributed GPU compute; serving regions are not published. Privacy policy: public LLM inference request/response content is not logged or stored; models run in TEEs (confidential compute). OpenRouter's provider list reports HQ US and no datacenter countries.
- Residency source
- https://chutes.ai/terms
Primary location is where inference servers run (server region, from the cited source; otherwise 'unknown'). Company HQ is secondary public company information. OpenRouter prices are volatile: refreshed twice daily and excluded from cheapest-price answers.
Blend input:output
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| Chutes Inference host | Gemma 4 31B (turbo, TEE) | $0.12 | $0.37 | $0.012 | $0.182 | 131K | unknown |
| Chutes Inference host | Qwen3.8 27B (TEE) | $0.039 | $1.25 | $0.0039 | $0.342 | 262K | unknown |
| Chutes Inference host | DeepSeek V4 Flash 0731 (TEE) | $0.44 | $1.32 | $0.044 | $0.66 | 1.048576M | unknown |
| Chutes Inference host | Kimi K2.6 (TEE) | $0.45 | $1.95 | $0.045 | $0.825 | 262K | unknown |
| Chutes Inference host | DeepSeek V3.2 (TEE) | $1.00 | $1.00 | $0.10 | $1.00 | 131K | unknown |
| Chutes Inference host | Qwen3.5 397B A17B (TEE) | $0.45 | $3.00 | $0.045 | $1.09 | 262K | unknown |
| Chutes Inference host | GLM 5.2 (TEE) | $1.25 | $3.95 | $0.125 | $1.93 | 1.048576M | unknown |
| Chutes Inference host | Kimi K3 (TEE) | $1.85 | $9.50 | $0.185 | $3.76 | 1.048576M | unknown |
Per 1M tokens, standard (non-promo) list prices; short-context / peak tier where tiered. USD unless shown with € or CHF: those are as published and not converted. Click a header to sort. 8 models.
* Blended assumes 3 input tokens for every output token: (3×input + output) / 4. Your real mix will differ, so use the cost calculator with your own token counts for a real estimate.