DeepSeek V4 Flash 0731 (TEE) API pricing
DeepSeek V4 Flash 0731 (TEE) by Chutes costs $0.44 per 1M input tokens and $1.32 per 1M output tokens (1M in + 1M out = $1.76).
- API model id
deepseek-ai/DeepSeek-V4-Flash-0731-TEE- Input / 1M
- $0.44
- Output / 1M
- $1.32
- Cached input / 1M
- $0.044
- Context window
- 1.048576M
- Notes
- Chutes pay-as-you-go, USD per 1M tokens from Chutes' public models API (also quoted in TAO); pricing page says rates are pulled live from its pricing API. Runs in a TEE (confidential compute), served fp8.
- Source
- https://llm.chutes.ai/v1/models
- Provider type
- Inference host (HQ: unknown)
- Regions
- unknown
- EU data residency
- unknown — 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.
- Last verified
- 2026-10-20
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Chutes | DeepSeek V4 Flash 0731 (TEE) | $0.77 |
Uses standard list prices (no caching, batch or off-peak discounts). € and CHF rows are priced in that currency by the provider and not converted, so compare them with care.
Other Chutes models
- Gemma 4 31B (turbo, TEE): $0.12 / $0.37
- Qwen3.8 27B (TEE): $0.039 / $1.25
- DeepSeek V3.2 (TEE): $1.00 / $1.00
- Kimi K2.6 (TEE): $0.45 / $1.95
- Qwen3.5 397B A17B (TEE): $0.45 / $3.00
- GLM 5.2 (TEE): $1.25 / $3.95
- Kimi K3 (TEE): $1.85 / $9.50