Qwen3.5-397B-A17B (TEE)

Name: qwen3.5-397b-a17b-tee
Brand: Qwen

Qwen

qwen3.5-397b-a17b-tee

Confidential

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 SayGM

-56.7%

$0.45$0.19

Cached

$0.225$0.097

Out

$3.00$1.30

per Mtok*

SayGM vs. list price

SayGM's best available rate for qwen3.5-397b-a17b-tee next to the published list price — 56.7% off.

Dimension	SayGM price	List price
Input	$0.19467per Mtok	$0.45
Output	$1.2978per Mtok	$3.00
Cache read	$0.097335per Mtok	$0.225

//01

Recent effective price

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

Input

$0.34

$0.45

Cached input

$0.190

$0.225

Output

$1.45

$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 168 windows: 490 requests and 1,273,555 input-side tokens, short of the 2,000,000 tokens the window walks for. Most recent window closed 2026-08-26 14:17 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	56.7% off	5.6 s	71 tps	93.8%	$0.19	$0.097	$1.30
Provider 2	4.2% off	3.2 s	72 tps	100.0%	$0.43	$0.216	$2.87
Provider 3	4.2% off	6.0 s	61 tps	95.2%	$0.43	$0.216	$2.87

//03

Performance

Measured on the requests SayGM routed to this model.

Throughput: 60.7 tok/sover 143 requests
Time to first token: 4.6 sover 149 requests
Request success rate: 96.0% over 101 requests

107 requests · 620,102 tokens billed · last 12 windowsWindow closed 2026-08-26 14:17 UTC

//04

Benchmarks

Fixed-seed suites SayGM runs against this model.

GPQA-Diamond2026-08-21

89.6%

99.0% answered · 0.0% refused

MATH-5002026-08-21

90.6%

99.0% answered · 0.0% refused

Frequently asked questions

How much does qwen3.5-397b-a17b-tee cost on SayGM?

The best available rate for qwen3.5-397b-a17b-tee on SayGM right now is $0.19 per million input tokens and $1.30 per million output tokens.

How much cheaper is SayGM than list price?

SayGM's best available rate for qwen3.5-397b-a17b-tee is 56.7% off list price.

Is qwen3.5-397b-a17b-tee OpenAI-compatible on SayGM?

Yes. qwen3.5-397b-a17b-tee is served on SayGM's OpenAI-compatible chat/completions surface, so an unmodified OpenAI SDK pointed at SayGM's base URL works with it.