Chutes · Confidential

zai-org/GLM-5.2-TEE

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

Tool calling: yes
Image input: yes

Released

Jun 2026

Modalities

Text · Tool calling · Image input

Best price on gm

-52.5%

$1.25$0.59

Cached

$0.625$0.297

Out

$3.95$1.88

per Mtok*

//01

Recent effective price

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

Input

$0.92

$1.25

Cached input

$0.466

$0.625

Output

$2.85

$3.95

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 13 windows: 1,872 requests and 2,096,542 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	52.5% off	4.7 s	14 tps	100.0%	$0.59	$0.297	$1.88
Provider 2	52.5% off	2.1 s	30 tps	100.0%	$0.59	$0.297	$1.88
Provider 3	4.0% off	28.1 s	15 tps	100.0%	$1.20	$0.600	$3.79
Provider 4	—	2.3 s	27 tps	100.0%	$1.25	$0.625	$3.95
Provider 5	—	15.6 s	26 tps	100.0%	$1.25	$0.625	$3.95

//03

Performance

Measured on the requests gm routed to this model.

Throughput: 18.1 tok/sover 10,242 requests
Time to first token: 10.2 sover 10,292 requests
Request success rate: 100.0% over 10,300 requests

1,615 requests · 3,419,311 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.