Chutes · Confidential

moonshotai/Kimi-K3-TEE

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

Tool calling: yes
Image input: yes

Released

Jul 2026

Modalities

Text · Tool calling · Image input

Best price on gm

-55.5%

$3.00$1.33

Cached

$1.50$0.67

Out

$15.00$6.67

per Mtok*

//01

Recent effective price

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

Input

$2.07

$3.00

Cached input

$1.00

$1.50

Output

$9.84

$15.00

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 11 windows: 1,135 requests and 2,004,619 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	3.1 s	23 tps	100.0%	$1.33	$0.67	$6.67
Provider 2	53.5% off	1.8 s	19 tps	100.0%	$1.39	$0.70	$6.97
Provider 3	52.5% off	2.4 s	22 tps	100.0%	$1.42	$0.71	$7.12
Provider 4	6.0% off	3.5 s	22 tps	100.0%	$2.82	$1.41	$14.09
Provider 5	4.0% off	2.0 s	29 tps	100.0%	$2.88	$1.44	$14.39
Provider 6	—	2.2 s	29 tps	100.0%	$3.00	$1.50	$15.00

//03

Performance

Measured on the requests gm routed to this model.

Throughput: 23.4 tok/sover 6,753 requests
Time to first token: 2.2 sover 6,601 requests
Request success rate: 100.0% over 6,777 requests

1,249 requests · 4,515,306 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.