Free to start

Chutes

Try Chutes on us. Starter credit covers your first requests, then one key reaches all 13 Chutes models, with the privacy posture shown on every route.

Chuteschutes

Confidential ZDR

All providers

These privacy labels describe Chutes, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.

Provider	Chutes
API operator country	US Legal home of the API operator, not an inference-location guarantee.
Headquarters	Not verified
Routing status	Active
Provider website	https://chutes.ai/
Models	13 public models
Credits routes	13
Zero data retention	yes All routes
Verified confidential inference	Verified
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

Inference locations

Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.

usage.provider_usage.gateway_region identifies the TrustedRouter gateway, not the provider's inference location. A value such as europe-west4 does not mean the model ran in Europe. usage.inference_location.serving_region remains null when the provider has not reported it. Older gateways may return the gateway-only field as provider_usage.region.

Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.

Declared countries or regions: Not verified
No inference-location declaration has been verified for this provider.
Can locations change?: Not verified. Do not assume that the serving location is fixed.
Provider region pinning: Not verified.
Pinning through TrustedRouter: No verified provider-specific location pin documented here.
Infrastructure declaration: Inference location not verified; no country-specific residency commitment.
Evidence: Not yet reviewed.

Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.

Measured performance

27 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	6896 ms
Effective throughput	21 tok/s n=5
Uptime	85.19%

Model	p50 TTFT	Effective throughput	Uptime	Config excluded	Availability samples
mistralai/mistral-nemo	5532 ms	—	100.00%	—	2
deepseek/deepseek-v4-flash-0731	5841 ms	—	50.00%	—	2
nvidia/nemotron-3-nano-omni	6044 ms	—	100.00%	—	3
qwen/qwen3-32b	6280 ms	—	100.00%	—	2
qwen/qwen3.6-27b	6896 ms	—	100.00%	—	3
google/gemma-4-31b-turbo	7388 ms	—	100.00%	—	2
qwen/qwen3.8-27b	8417 ms	—	100.00%	—	3
z-ai/glm-5.2	10142 ms	19 tok/s n=2	100.00%	—	2
moonshotai/kimi-k2.6	13293 ms	30 tok/s n=2	100.00%	—	2
z-ai/glm-5.1	40528 ms	—	100.00%	—	3
moonshotai/kimi-k3	—	21 tok/s n=1	—	—	0
qwen/qwen3.5-397b-a17b	—	—	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	Input	Cached input	Output
`deepseek/deepseek-v3.2` DeepSeek: DeepSeek V3.2 benchmarks	IQ 102#110	131,072	$1.055/1M	$0.1055/1M	$1.055/1M
`deepseek/deepseek-v4-flash-0731` DeepSeek: DeepSeek V4 Flash 0731	—	1,048,576	$0.4642/1M	$0.04642/1M	$1.3926/1M
`google/gemma-4-31b-turbo` google/gemma-4-31B-turbo	—	131,072	$0.1266/1M	$0.01266/1M	$0.39035/1M
`mistralai/mistral-nemo` Mistral: Mistral Nemo	—	131,072	$0.025848/1M	$0.01/1M	$0.103179/1M
`moonshotai/kimi-k2.6` MoonshotAI: Kimi K2.6 benchmarks	IQ 114#58	262,144	$0.47475/1M	$0.047475/1M	$2.05725/1M
`moonshotai/kimi-k3` MoonshotAI: Kimi K3	IQ 127#21	1,048,576	$1.95175/1M	$0.195175/1M	$10.0225/1M
`nvidia/nemotron-3-nano-omni` Nemotron-3-Nano-Omni-30B	—	131,072	$0.025848/1M	$0.01/1M	$0.103179/1M
`qwen/qwen3-32b` Qwen: Qwen3 32B	—	131,072	$0.10972/1M	$0.010972/1M	$0.43888/1M
`qwen/qwen3.5-397b-a17b` Qwen: Qwen3.5 397B A17B	—	262,144	$0.47475/1M	$0.047475/1M	$3.165/1M
`qwen/qwen3.6-27b` Qwen: Qwen3.6 27B	IQ 110#79	262,144	$0.26375/1M	$0.026375/1M	$2.11/1M
`qwen/qwen3.8-27b` Qwen: Qwen3.8 27B	IQ 116#52	65,536	$0.041145/1M	$0.01/1M	$1.31875/1M
`z-ai/glm-5.1` Z.ai: GLM 5.1 benchmarks	IQ 113#62	202,752	$1.0339/1M	$0.10339/1M	$3.2494/1M
`z-ai/glm-5.2` Z.ai: GLM 5.2 benchmarks	IQ 118#48	1,048,576	$1.31875/1M	$0.131875/1M	$4.16725/1M

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