ModelPickr

Models / Moonshot AI / Kimi K2 Thinking

Moonshot AI · kimi-thinking

Kimi K2 Thinking

Thinking Kimi model for slower research passes, planning, and hard technical questions

$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 Amazon Bedrock's rate, the provider closest to the median.

Provider input prices run from $0.60 to $0.83 per 1M tokens. Output prices run from $2.50 to $3.44.

Context
262,144
Max output
262,144
Cache read
—
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
—
Released
Nov 6, 2025
Updated in source
Nov 6, 2025
Knowledge
2024-08
Providers
11

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 Thinking

$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
Amazon Bedrockreference$0.60$2.50———
Charm Hyper$0.60$2.50$0.30——
DevPass$0.60$2.50$0.06——
Eden AI$0.60$2.50———
Kilo Gateway$0.60$2.50$0.15——
LLM Gateway$0.60$2.50$0.06——
Merge Gateway$0.60$2.50——deprecated
NanoGPT$0.60$2.50$0.15——
Novita AI$0.60$2.50$0.15——
OpenRouter$0.60$2.50$0.15——
AI/ML API$0.83$3.44$0.21——

Jobs this model qualifies for