Input
- Official Moonshot
- $3
- Here (−50%)
- $1.5
k3-256k
Kimi K3 (256K) API — price per token
The same Kimi K3 at the same rates, with a 256K accepted window — for harnesses that expect a smaller context than the 1M variant.
Pricing per 1M tokens
| Rate | Official Moonshot | Here (−50%) |
|---|---|---|
| Input | $3 | $1.5 |
| Cached input | $0.3 | $0.15 |
| Cache write | $3 | $1.5 |
| Output | $15 | $7.5 |
Cached input
- Official Moonshot
- $0.3
- Here (−50%)
- $0.15
Cache write
- Official Moonshot
- $3
- Here (−50%)
- $1.5
Output
- Official Moonshot
- $15
- Here (−50%)
- $7.5
Every request is metered at the official rate first, then the flat 50% B2C discount is subtracted before it touches your prepaid balance. Context window: 256K tokens. Max output: not published.
Best for
- Tools that cap or mis-handle a 1M-token window.
- Sessions where a smaller window keeps compaction predictable.
Good to know
- Cached input bills at 10% of input — caching is automatic on repeated prefixes.
- KIMI publishes no separate cache-write rate: a write is a cache miss and bills at the input rate.
How to use Kimi K3 (256K)
Create a free account, generate one key, and point any Anthropic-compatible tool at https://router.apitoken.sale with model ID kimi/k3-256k, authenticated with x-api-key. Kimi speaks the Anthropic Messages protocol, so the catalogue namespace in the model ID is what selects it — the base URL is the same one Claude uses. Eligible new accounts include $5 of platform bonus credit — enough to test the model before topping up.
Frequently asked questions
Does k3-256k cost less than k3?
No. It is the same model on the same rate card — $3.00/$15.00 officially, $1.50/$7.50 here. Only the accepted context differs.
When should I pick it over k3?
When your client compacts against the window it is told about: a harness configured for 256K will behave more predictably on this id than on the 1M one.
Run Kimi K3 (256K) on the Anthropic Messages API at a flat 50% off — instant key, prepaid balance, card or crypto.