Models / Moonshot AI / Kimi K2 Instruct 0905

Moonshot AI · kimi-k2

Kimi K2 Instruct 0905

September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding

$0.60 in · $2.50 out

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

Provider input prices run from $0.60 to $1.38 per 1M tokens. Output prices run from $2.50 to $4.13.

Context
262,144
Max output
98,304
Cache read
—
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
Modified MIT
Released
Sep 5, 2025
Updated in source
Sep 5, 2025
Knowledge
—
Providers
5

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 0905

$7.35

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
Kilo Gatewayreference$0.60$2.50———
Novita AI$0.60$2.50———
OpenRouter$0.60$2.50———
Prime Inference$0.60$2.50———
AI/ML API$1.38$4.13———

Jobs this model qualifies for