Models / Moonshot AI / Kimi K2 Instruct

Moonshot AI · kimi-k2

Kimi K2 Instruct

Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents

$0.50 in · $2.00 out

per 1M tokens · provider rate closest to the median. No first-party Moonshot AI price was listed. The reference price is Eden AI's rate, the provider closest to the median.

Provider input prices run from $0.40 to $0.57 per 1M tokens. Output prices run from $1.80 to $2.30.

Context
131,072
Max output
32,768
Cache read
—
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
Modified MIT
Released
Jul 11, 2025
Updated in source
Jul 11, 2025
Knowledge
—
Providers
3

Hugging Face weights

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.

Estimated monthly cost

Kimi K2 Instruct

$6.00

Cache hit is ignored because this model has no cache-read price.

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
NanoGPT$0.40$1.80$0.20——
Eden AIreference$0.50$2.00———
Novita AI$0.57$2.30———