Chutes · Confidential

zai-org/GLM-5.1-TEE

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

Tool calling: yes
Image input: yes

Released

Apr 2026

Modalities

Text · Tool calling · Image input

Best price on gm

-52.5%

$0.98$0.47

Cached

$0.49$0.23

Out

$3.08$1.46

per Mtok*

//01

Recent effective price

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

Input

$0.78

$0.98

Cached input

$0.38

$0.49

Output

$2.44

$3.08

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 11 windows: 1,233 requests and 2,007,592 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	2.9 s	49 tps	100.0%	$0.47	$0.23	$1.46
Provider 2	52.5% off	1.6 s	55 tps	100.0%	$0.47	$0.23	$1.46
Provider 3	4.0% off	2.3 s	54 tps	100.0%	$0.94	$0.47	$2.96
Provider 4	—	3.5 s	46 tps	100.0%	$0.98	$0.49	$3.08
Provider 5	—	3.0 s	55 tps	100.0%	$0.98	$0.49	$3.08

//03

Performance

Measured on the requests gm routed to this model.

Throughput: 34.0 tok/sover 6,047 requests
Time to first token: 3.1 sover 6,045 requests
Request success rate: 100.0% over 6,053 requests

1,348 requests · 3,744,181 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.