MoonshotTool use

Kimi K2 Thinking pricing

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in... Below you will find 6 current rows with input and output dollars per million. Right now the lowest input is $0.600 and the lowest output is $1.20.

262K context·6 providers·save up to 52% vs native via Gmi·verified Apr 9, 2026
Best input$0.600per 1M tokens · Baseten
Best output$1.20per 1M tokens · Gmi

Pricing across providers

Every row is a seller of Kimi K2 Thinking with token pricing we track. The cheapest input in this snapshot is from Baseten. The bar chart shows the same input and output dollars per million for a quick scan.

B
Baseten
Input / 1M
$0.600
Output / 1M
$2.50
O
Openrouter
Input / 1M
$0.600
Output / 1M
$2.50
M
Moonshotnative
Input / 1M
$0.600
Output / 1M
$2.50
Cached in: $0.150
FA
Fireworks AI
Input / 1M
$0.600
Output / 1M
$2.50
N
Novita
Input / 1M
$0.600
Output / 1M
$2.50
G
Gmi
Input / 1M
$0.800
Output / 1M
$1.20

Input vs output · per provider

Cost calculator

Pick any of the providers above and type how many tokens you expect per day, week, or year. We turn that into rough dollar totals for Kimi K2 Thinking.

Provider

In: $0.600/M·Out: $2.50/M

0.060000¢ / req

0.125000¢ / req

Daily
$19
Monthly
$555
Annual
$6.8K

Model specifications

Context length, caps, and capability flags for Kimi K2 Thinking. Values follow the main provider (Moonshot) record in our index.

Context window
262,144 tokens
Max output
262,144 tokens
Vision (images)
No
Tool / function calling
Yes
Streaming
No
Released
Nov 2025
Primary provider
Moonshot
Model family
N/A

Compare Kimi K2 Thinking

These links open full side by side pages for Kimi K2 Thinking. We picked pairs that people often shop together. 6 ready to open.

Frequently asked questions

Answers pull from the same numbers you see on this page. The short model note from our index: Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced...

Kimi K2 Thinking costs $0.60 per million input tokens and $2.50 per million output tokens via the native API. Prompt caching reduces input costs to $0.15/M tokens.

Also from Moonshot

Other models by Moonshot with live pricing in our catalog.