modelbenchmark.io

Kimi K3.1 Pro Highspeed

Kimi · kimi-k3-1-pro-highspeed

Compare

Multimodal Kimi model with 1M context and always-on reasoning for coding, 3D creation, financial research, and agentic work

Specification

moonshotai listing

Context
1M
Max output
1M
Released
2026-10-23
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, image, video
Output
text

Price

US dollars per million tokens · moonshotai list price

Input
$4.00
Output
$20.00
Cache read
$0.20
Cache write
$4.00

Available from 10 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
moonshotaivendor$4.00$20.00$0.20$4.001M1M—
moonshotai-cn$3.8874$20.3342$0.1944$3.88741M1M—
llmgateway$4.00$20.00$0.20$4.001M1M—
llmgateway-providers$4.00$20.00$0.20$4.001M1M—
llmgateway-providers · runpod$4.00$20.00$0.20—1M1M—
nano-gpt · moonshotai$4.00$20.00$0.20$4.001M1M—
novita-ai · moonshotai$4.00$20.00$0.20$4.001M1M—
requesty$4.00$20.00$0.20$4.001M1M—
vercel · moonshotai$4.00$20.00$0.20$4.001M1M—
venice$7.50$37.50$0.75—1M131K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-10-24veniceCache read$0.60
2026-10-31veniceCache read$0.75
2026-10-24veniceInput$6.00
2026-10-31veniceInput$7.50
2026-10-24veniceOutput$30.00
2026-10-31veniceOutput$37.50

Other listings of this model

same model, different key

More from Kimi

most-hosted first