Kimi K2 Thinking
Kimi K2 Thinking is the latest, most capable version of open-source thinking model developed by MoonshotAI.
text → text · made by Moonshot AI
Sold by 20 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock cloud | batch | $0.3per Mtok in$1.25per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| AWS Bedrock cloud | flex | $0.3per Mtok in$1.25per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| AWS Bedrock cloud | standard | $0.6per Mtok in$2.5per Mtok outmodels.dev · read 2026-10-31 |
| Google Vertex AI cloud | standard | $0.6per Mtok in$2.5per Mtok out$0.06per Mtok cachedmodels.dev · read 2026-10-31 |
| Microsoft Azure AI cloud | standard | $0.6per Mtok in$2.5per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| AWS Bedrock cloud | priority | $1.05per Mtok in$4.38per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| Crusoe cloud | standard | $2.5per Mtok in$2.5per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| DeepInfra aggregator | standard | $0.47per Mtok in$2per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Vercel AI Gateway 0 ways | $0.47per Mtok in$2per Mtok out$0.14per Mtok cached | |
| Vercel AI Gateway aggregatornot on the seller's list today | standard | $0.47per Mtok in$2per Mtok out$0.14per Mtok cachedai-gateway.vercel.sh · read 2026-08-25 |
| Baseten aggregator | standard | $0.6per Mtok in$2.5per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| ElectronHub aggregator | standard | $0.6per Mtok in$2.5per Mtok outapi.electronhub.ai · read 2026-10-31 |
| Featherless AI aggregator | standard | $0.6per Mtok in$2.5per Mtok outapi.featherless.ai · read 2026-09-20 |
| Fireworks AI aggregator | standard | $0.6per Mtok in$2.5per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| Hugging Face Inference Providers aggregator | standard | $0.6per Mtok in$2.5per Mtok out$0.15per Mtok cachedmodels.dev · read 2026-10-31 |
| IO.NET aggregator | standard | $0.6per Mtok in$2.5per Mtok out$0.3per Mtok cached$1.1per Mtok cache writemodels.dev · read 2026-10-31 |
| Nous Research aggregator | standard | $0.6per Mtok in$2.5per Mtok out$0.15per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| Novita AI aggregator | standard | $0.6per Mtok in$2.5per Mtok out$0.15per Mtok cachedapi.novita.ai · read 2026-08-25 |
| OpenRouter 2 ways | $0.6per Mtok in$2.5per Mtok out$0.15per Mtok cached | |
| OpenRouter aggregator | standard | $0.6per Mtok in$2.5per Mtok out$0.15per Mtok cachedopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | google-vertex | $0.6per Mtok in$2.5per Mtok outopenrouter.ai · read 2026-08-25 |
| PPIO aggregator | standard | $4per Mtok in$16per Mtok outapi.ppinfra.com · read 2026-10-31 |
Measured 9 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 15thof 23 | Cl bench — Epoch AI | Overall | 0.176 |
| 24thof 49 | Metr time horizons — Epoch AI | average_score | 0.592 |
| 37thof 101 | FrontierMath (Tiers 1-3) | mean_score | 21.404 |
| 65thof 72 | Frontiermath tier 4 — Epoch AI | mean_score | 0 |
| 101stof 173 | Weirdml — Epoch AI | Accuracy | 42.79 |
| 103rdof 132 | Ale bench — Epoch AI | Performance | 597.5 |
| 114thof 202 | Terminalbench — Epoch AI | Accuracy mean | 0.357 |
| 133rdof 169 | Design Arena · website (models) | Elo | 1111 |
| 134thof 163 | Artificial Analysis · Coding Index | Index | 21 |
About
Kimi K2 Thinking — a text model from Moonshot AI, sold by 15 companies from $0.47 in and $2 out per million tokens, placed 37th of 101 on FrontierMath (Tiers 1-3).
It takes text and returns text, with a context window of 32,768 tokens. It was published in November 2024, trained on material up to August 2024. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning and agents. Fifteen companies sell it. The cheapest is $0.47 in and $2 out per million tokens at DeepInfra. Beside the standard rate there are batch, flex, faster and separately routed lanes. It has been measured on 9 boards, and stands best at 37th of 101 on FrontierMath (Tiers 1-3).
Every current figure
- Maker
- Moonshot AI
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 32,768 tokens
- Published
- November 2024
- Knowledge to
- August 2024
- Parameters
- 1058 billion
- Licence
- not read
- Sellers
- 15
- Maker's own price
- not read
- Price
- $0.47 in and $2 out per million tokens — DeepInfra
- Boards
- 9
- Best place
- 37th of 101 — FrontierMath (Tiers 1-3)
Known as 3 names
K2 Thinkingmoonshotai/Kimi-K2-ThinkingKimi-K2-Thinking