Kimi API pricing: every model, every rate
Kimi built its reputation on very long context windows. Several tiers below include dedicated coding and high-speed variants.
Full rate card
17 billable models. 0 carry a rate verified against the vendor's own published pricing; the rest are gateway rates only. USD per 1M tokens, verified 2026-09-16.
| Model | Input | Output | Out/In | Official (in / out) |
|---|---|---|---|---|
moonshot-v1-128k | $12 | $12 | 1.0× | not verified |
kimi-k2.7-code-highspeed | $6.5 | $27 | 4.2× | not verified |
moonshot-v1-32k | $2.4 | $2.4 | 1.0× | not verified |
Kimi-K2-Instruct | $2 | $8 | 4.0× | not verified |
Moonshot-Kimi-K2-Instruct | $2 | $8 | 4.0× | not verified |
kimi-k2-0711-preview-search | $2 | $8 | 4.0× | not verified |
kimi-k3 | $1.5 | $7.5 | 5.0× | not verified |
moonshot-v1-8k | $1.2 | $1.2 | 1.0× | not verified |
kimi-k2.6 | $0.475 | $1.9731 | 4.2× | not verified |
kimi-k2.7-code | $0.475 | $1.9731 | 4.2× | not verified |
kimi-k2 | $0.3 | $1.2 | 4.0× | not verified |
kimi-k2-0711-preview | $0.3 | $1.2 | 4.0× | not verified |
kimi-k2-0905 | $0.3 | $1.2 | 4.0× | not verified |
kimi-k2-250711 | $0.3 | $1.2 | 4.0× | not verified |
kimi-k2-250905 | $0.3 | $1.2 | 4.0× | not verified |
kimi-k2-thinking | $0.3 | $1.2 | 4.0× | not verified |
kimi-k2.5 | $0.3 | $1.575 | 5.2× | not verified |
Output is billed at a multiple of input on most models. The Out/In column is that multiple — it matters more than the input price once output dominates your bill.
Across 17 billable models the rate spans $0.3 (kimi-k2) to $12 (moonshot-v1-128k) per million input tokens — a 40× spread. Picking the wrong tier is usually the single most expensive mistake here.
What Moonshot is good at
Kimi is the usual pick when you need a long context window without frontier-model pricing.
See all 827 models → or use the cost calculator with your own token split.