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.
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.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
B Baseten | $0.600 | $2.50 | — | — |
O Openrouter | $0.600 | $2.50 | — | — |
M Moonshotnative | $0.600 | $2.50 | $0.150 | — |
FA Fireworks AI | $0.600 | $2.50 | — | — |
N Novita | $0.600 | $2.50 | — | — |
G Gmi | $0.800 | $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
0.060000¢ / req
0.125000¢ / req
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.
- Kimi K2 Thinking vs GPT-4o
Kimi K2 Thinking 75% cheaper on output
- Kimi K2 Thinking vs GPT-4o mini
GPT-4o mini 76% cheaper on output
- Kimi K2 Thinking vs Claude Sonnet 4.6
Kimi K2 Thinking 83% cheaper on output
- Kimi K2 Thinking vs Gemini 2.0 Flash
Gemini 2.0 Flash 84% cheaper on output
- Kimi K2 Thinking vs o3
Kimi K2 Thinking 68% cheaper on output
- Kimi K2 Thinking vs Llama 3.1 70B
Compare pricing side by side
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...
Also from Moonshot
Other models by Moonshot with live pricing in our catalog.