Moonshot AI › Kimi K3.1 Pro Highspeed › Pricing
Kimi K3.1 Pro Highspeed pricing
API list price by Moonshot AI · checked Oct 26, 2026
$4 / $20per 1M tokens in / out
$0.20cache read · −95%
Price sheetper 1M tokens
| Input | $4 | list |
| Output | $20 | |
| Cache read | $0.20 | −95% vs input |
| Cache write · 5 min | $4 | 0% vs input |
| Cache write · 1 h | $8 | +100% vs input |
| Context | 1M | tokens |
Global Kimi API standard pay-as-you-go USD / million tokens, before tax; flat across context lengths. Input is cache miss; cached input and separate 5m/1h writes retained. Membership/subscription tariffs excluded.
Where to buy1 provider · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| Novita | $4 | $20 | — |
In Moonshot AI's line-upper 1M in / out
| Kimi K2.7 Code | $0.95 / $4 | −79% |
| Kimi K2.7 Code Highspeed | $1.90 / $8 | −57% |
| Kimi K3.1 Pro | $2 / $10 | −50% |
| Kimi K3 | $3 / $15 | −25% |
| Kimi K3.1 Pro Highspeed | $4 / $20 | this model |
Pricing questions
How much does Kimi K3.1 Pro Highspeed cost?›
$4 per 1M input tokens and $20 per 1M output tokens. Cached input is $0.20.
Is Kimi K3.1 Pro Highspeed free to use?›
There is no free API tier.
How much does prompt caching save?›
Cache reads cost $0.20 per 1M, 95% below the input price. Writing to the cache costs $4 per 1M (5m TTL).