Chutes · Confidential

moonshotai/Kimi-K2.6-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%

$0.66$0.31

Cached

$0.33$0.16

Out

$3.50$1.66

per Mtok*

//01

Recent effective price

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

Input

$0.40

$0.66

Cached input

$0.20

$0.33

Output

$2.12

$3.50

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: 1,485 requests and 2,059,247 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	2.0 s	53 tps	100.0%	$0.31	$0.16	$1.66
Provider 2	52.5% off	1.7 s	57 tps	100.0%	$0.31	$0.16	$1.66
Provider 3	6.0% off	2.7 s	49 tps	100.0%	$0.62	$0.31	$3.29
Provider 4	4.0% off	1.6 s	45 tps	100.0%	$0.63	$0.32	$3.36
Provider 5	—	1.8 s	49 tps	100.0%	$0.66	$0.33	$3.50

//03

Performance

Measured on the requests gm routed to this model.

Throughput: 43.2 tok/sover 6,762 requests
Time to first token: 2.3 sover 6,755 requests
Request success rate: 100.0% over 6,768 requests

1,631 requests · 5,803,413 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.