Chutes · Confidential

Qwen/Qwen3.5-397B-A17B-TEE

Open weights, run inside a TEE. Inference happens sealed, so the prompt stays inside the enclave.

Tool calling: yes
Image input: yes

Released

Feb 2026

Modalities

Text · Tool calling · Image input

Best price on gm

-55.5%

$0.45$0.20

Cached

$0.225$0.100

Out

$3.00$1.33

per Mtok*

//01

Recent effective price

What buyers have actually paid on this model recently, across every provider and cache hits.

Input

$0.29

$0.45

Cached input

$0.151

$0.225

Output

$2.00

$3.00

How the effective price is calculated

Requests are load balanced across every provider serving this model, each offering its own rate, so what you pay is a blend rather than a single number. These are the blended rates actually paid — priced at what a provider offered, capped at list.

Measured over 8 windows: 1,100 requests and 2,099,005 input-side tokens. Most recent window closed 2026-08-11 02:24 UTC.

//02

Who's serving this model

Every provider currently serving this model, ranked by discount.

Provider	Discount	Latency	Throughput	Uptime	In	Cached	Out
Provider 1	55.5% off	2.0 s	134 tps	100.0%	$0.20	$0.100	$1.33
Provider 2	52.5% off	1.8 s	28 tps	100.0%	$0.21	$0.107	$1.42
Provider 3	4.0% off	2.3 s	144 tps	100.0%	$0.43	$0.216	$2.88

//03

Performance

Measured on the requests gm routed to this model.

Throughput: 98.3 tok/sover 6,053 requests
Time to first token: 1.8 sover 6,046 requests
Request success rate: 100.0% over 6,054 requests

1,611 requests · 6,151,472 tokens billed · last 12 windowsWindow closed 2026-08-11 02:24 UTC

//04

Benchmarks

Fixed-seed suites gm runs against this model.

No benchmark run has been published for this model.