OpenAI compatible API · Attested · Public status

Chutes

Explore Chutes models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

Chuteschutes

Confidential

All providers

Provider	Chutes
Provider website	https://chutes.ai/
Models	10 public models
Prepaid routes	10
BYOK routes	10
Zero data retention	yes
Confidential compute	yes
Provider E2EE	yes
Policy note	TrustedRouter encrypts each request to an attested Chutes workload and verifies Intel TDX plus NVIDIA GPU attestation inside the TrustedRouter enclave before sending content. Verification fails closed. Chutes also documents no prompt/output storage or training. Policy source

Measured performance

39 samples

Continuously sampled across Chutes's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.

p50 TTFT	8224 ms
Effective throughput	—
Uptime	46.15%

Model	p50 TTFT	p50 TTFB	Effective throughput	Uptime	Config excluded	Availability samples
moonshotai/kimi-k2.6	11377 ms	11377 ms	—	100.00%	—	5
deepseek/deepseek-v3.2	13440 ms	13439 ms	—	100.00%	—	4
qwen/qwen3.5-397b-a17b	13978 ms	13978 ms	—	100.00%	1 `provider_error`	1
z-ai/glm-5.2	7862 ms	7862 ms	—	85.71%	4 `provider_error`	7
z-ai/glm-5.1	8224 ms	8224 ms	—	50.00%	—	4
google/gemma-4-31b-turbo	—	—	—	0.00%	—	5
mistralai/mistral-nemo	—	—	—	0.00%	—	4
qwen/qwen3-235b-a22b-thinking-2507	—	—	—	0.00%	—	3
qwen/qwen3-32b	—	—	—	0.00%	—	3
qwen/qwen3.6-27b	—	—	—	0.00%	—	3

Chutes performance history · Full provider & model leaderboard.

Provider models

Models served by Chutes.

Each row links to pricing, provider, benchmark, and API pages for the model.

Model	AI IQ	Context	Endpoints	Prompt	Completion	Routes
`deepseek/deepseek-v3.2` DeepSeek: DeepSeek V3.2 benchmarks providers pricing	IQ 103#64	163,840	2	$1.055/1M	$1.055/1M	prepaid BYOK
`google/gemma-4-31b-turbo` google/gemma-4-31B-turbo providers pricing	—	131,072	2	$0.1266/1M	$0.39035/1M	prepaid BYOK
`mistralai/mistral-nemo` Mistral: Mistral Nemo providers pricing	—	131,072	2	$0.025848/1M	$0.103179/1M	prepaid BYOK
`moonshotai/kimi-k2.6` MoonshotAI: Kimi K2.6 benchmarks providers pricing	IQ 119#23	262,144	2	$0.6119/1M	$3.587/1M	prepaid BYOK
`qwen/qwen3-235b-a22b-thinking-2507` Qwen: Qwen3 235B A22B Thinking 2507 providers pricing	—	262,144	2	$0.31534/1M	$1.261464/1M	prepaid BYOK
`qwen/qwen3-32b` Qwen: Qwen3 32B providers pricing	—	131,072	2	$0.10972/1M	$0.43888/1M	prepaid BYOK
`qwen/qwen3.5-397b-a17b` Qwen: Qwen3.5 397B A17B providers pricing	—	262,144	2	$0.47475/1M	$3.165/1M	prepaid BYOK
`qwen/qwen3.6-27b` Qwen: Qwen3.6 27B providers pricing	IQ 111#47	262,144	2	$0.3165/1M	$2.11/1M	prepaid BYOK
`z-ai/glm-5.1` Z.ai: GLM 5.1 benchmarks providers pricing	IQ 114#38	204,800	2	$1.0339/1M	$3.2494/1M	prepaid BYOK
`z-ai/glm-5.2` Z.ai: GLM 5.2 benchmarks providers pricing	IQ 120#19	1,048,576	2	$1.31875/1M	$4.16725/1M	prepaid BYOK

Questions

Does Chutes have zero data retention?

TrustedRouter records Chutes as supporting provider-level zero data retention based on the policy source linked on this page. This is a provider policy claim, separate from TrustedRouter's content-stateless real-time gateway and from end-to-end confidential compute.

Is Chutes end-to-end encrypted?

TrustedRouter records Chutes as supporting provider-side confidential compute and end-to-end encrypted inference. The route-specific model page shows whether that protection applies to a particular endpoint.

Which Chutes models are available through TrustedRouter?

This page currently lists 10 public Chutes models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.