Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
Specification
most-agreed values
Context
1M
Max output
131K
Released
2026-07-16
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image, video
Output
text
Price
US dollars per million tokens · most-agreed
Input
$4.50
Output
$22.50
Cache read
$0.45
Cache write
$4.50
Available from 7 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| neuralwatt | $3.00 | $15.00 | $0.30 | — | 1M | 1M | — |
| fireworks_ai | $4.50 | $22.50 | $0.45 | — | 1M | 131K | — |
| fireworks-ai · accounts | $4.50 | $22.50 | $0.45 | — | 1M | 131K | — |
| llmgateway | $4.50 | $22.50 | $0.45 | — | 1M | 131K | — |
| llmgateway-providers | $4.50 | $22.50 | $0.45 | — | 1M | 1M | — |
| pioneer · moonshotai | $4.50 | $22.50 | $0.45 | $4.50 | 1M | 131K | — |
| vercel · moonshotai | $4.50 | $22.50 | $0.45 | — | 1M | 131K | — |
Other listings of this model
this page is one of them
The corpus files Kimi K3 under several keys. This page is the kimi-k3-fast listing. The full record — every host, every price and every benchmark score — is on the main Kimi K3 page.
More from Kimi
most-hosted first