Models / Moonshot AI / Kimi K2.8 Preview

Moonshot AI · kimi-k2

Kimi K2.8 Preview

Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code

$0 in · $0 out

per 1M tokens · listed at $0. Every priced listing in Models.dev is $0. That can mean a free model, or a price the source has not filled in.

Context
1,048,576
Max output
—
Cache read
$0
Cache write
$0
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
Yes
Open weights
No
License
—
Released
Sep 11, 2026
Updated in source
Sep 11, 2026
Knowledge
—
Providers
2

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
Kimi For Codingreference$0$0$0$0—
Kimi For Coding$0$0$0$0—