Open-weight model inference on TEE GPUs
Chutes (chutes.ai) is an inference platform for open-weight models. Workloads run inside Trusted Execution Environments (TEEs) on GPU hardware, with cryptographic attestation of model and input confidentiality. The API is OpenAI-compatible and pricing is per token with no minimum commitment.
Open-weight inference platform running workloads inside TEEs with cryptographic attestation.
| Model | Modality | Tier | Price | Cached /1M | TTFT | Throughput | Context | Intel. | Caps | |
|---|---|---|---|---|---|---|---|---|---|---|
Mistral-Nemo-Instruct-2407 Mistral | Chat | budget | $0.02/ $0.10 in / out per 1M EST Oct 2026 | — | — | — | 131K | — | ||
Qwen3.8-27B Qwen 3 | Chat | budget | $0.04/ $1.25 in / out per 1M EST Oct 2026 | — | — | — | 262K | — | ||
Qwen3-32B Qwen 3 | Chat | efficient | $0.10/ $0.42 in / out per 1M EST Oct 2026 | — | — | — | 41K | — | ||
gemma-4-31b-turbo Gemma 4 | Chat | efficient | $0.12/ $0.37 in / out per 1M EST Oct 2026 | — | — | — | 131K | — | ||
Qwen3.6-27B Qwen 3 | Chat | efficient | $0.25/ $2.00 in / out per 1M EST Oct 2026 | — | — | — | 262K | — | ||
DeepSeek-V4-Flash-0731 DeepSeek | Chat | efficient | $0.44/ $1.32 in / out per 1M EST Oct 2026 | — | — | — | 1.0M | — | ||
Kimi-K2.6 Kimi | Chat | efficient | $0.45/ $1.95 in / out per 1M EST Oct 2026 | — | — | — | 262K | — | ||
GLM-5.1 GLM | Chat | efficient | $0.98/ $3.08 in / out per 1M EST Oct 2026 | — | — | — | 203K | — | ||
GLM-5.2 GLM | Chat | efficient | $1.25/ $3.95 in / out per 1M EST Oct 2026 | — | — | — | 1.0M | — | ||
Kimi-K3 Kimi | Chat | advanced | $1.85/ $9.50 in / out per 1M EST Oct 2026 | — | — | — | 1.0M | — |
Chutes is an inference API provider that hosts open-weight and third-party large language models. Common use cases include Open-weight inference, Privacy-sensitive workloads, Serverless LLM. Headquartered in Remote, founded 2024. All models are accessible via a REST API compatible with standard OpenAI-style request formats, enabling drop-in integration with most LLM frameworks and orchestration tools.
Chutes competes with OpenAI, Anthropic, Google, Groq, Together AI, Mistral, Cohere, and other inference API providers across dimensions of price, throughput, latency, context window, and model intelligence. Use the LLM provider comparison tool to see Chutes token pricing, latency, and throughput side-by-side with any other provider. The full LLM pricing table shows all providers ranked by input token cost, output token cost, and throughput in a single sortable view.
Chutes offers 10 models across 1 advanced, 7 efficient, 2 budget tiers. For teams running high-volume inference workloads, prompt caching and batch API endpoints can reduce effective input token costs by 50–90% — check the context window cost guide for a full breakdown of caching economics.
Chutes charges separately for input (prompt) and output (completion) tokens, priced per 1M tokens in USD. Output tokens are typically 3–5× more expensive than input tokens due to the compute cost of autoregressive generation. The cheapest Chutes input rate is currently $0.02/1M tokens. Prices shown are sourced from Chutes's public pricing page and updated every 15 minutes. Need help estimating your spend? Read the LLM API cost calculator guide — it covers tokens, context windows, prompt caching, and batch discounts with worked examples for RAG, chat history, and document processing workloads.
Context window size directly affects both capability and cost — every token in the context window is charged as an input token. Chutes's largest context window is 1.0M tokens. For RAG and document processing workloads, longer context windows enable richer retrieval but increase per-call costs proportionally. Prompt caching — where supported — stores the KV state of repeated prefixes and charges 75–90% less for cache hits, making it the most impactful cost optimization for applications with consistent system prompts or retrieved documents. See the LLM context window cost guide for a full analysis of how context length affects your API bill.
Managed inference APIs like Chutes eliminate infrastructure overhead — no GPU provisioning, driver management, or model serving stack to maintain. The trade-off is cost at scale: a single H100 at ~$2.50/hr can serve ~500K tokens/min of Llama 3.3 70B, which at Chutes API rates would cost significantly more per token. The break-even point depends on your request volume, latency requirements, and engineering capacity. For teams processing fewer than ~10M tokens/day, managed APIs are almost always cheaper when total cost of ownership is considered. Above that threshold, self-hosted inference on rented GPU compute typically wins on unit economics. Read the cheapest GPU cloud guide for a full break-even analysis. Historical Chutes token price data is available in the LLM price history charts.
Side-by-side token pricing, latency, throughput, and context window. View all LLM provider comparisons →