Moonshot AI · Released Nov 6, 2025Kimi K2 Thinking
Thinking Kimi model for slower research passes, planning, and hard technical questions.
- Capability
- 146.0ECI · #72 of 148
- Input
- $0.60per 1M tokens
- Output
- $2.50per 1M tokens
- Context
- 262K262K max output
What it costs
- Input
- $0.60per million tokens
- Output
- $2.50per million tokens
- Blended (3:1)
- $1.07pricier than 58% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $2.45 |
| Team assistant25M input + 5M output tokens | $27.50 |
| Production app250M input + 50M output tokens | $275.00 |
Median of 10 paid API providers on models.dev.
Independent benchmarks
#72 of 148 scored models
The shaded band is Epoch AI’s confidence range (143.4–147.6); the tick marks the median scored model.
Scores from Epoch AI, run independently of Moonshot AI.
The details
- Lab
- Moonshot AI
- Released
- Nov 6, 2025
- Knowledge cutoff
- Aug 2024
- Context window
- 262,144 tokens
- Max output
- 262,144 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- Always on
- Tool calling
- Yes
- Structured output
- No
- Weights
- Open weights
- Availability
- 10 API providerslisted on models.dev
What Moonshot AI claims
Published by the lab at launch. Settings vary, so compare these only with care.
| Benchmark | Score | Setting | Source |
|---|---|---|---|
| SWE-Bench Verified | 71.3 resolved | — | Source |
More from Moonshot AI
About Kimi K2 Thinking
How much does Kimi K2 Thinking cost?
Kimi K2 Thinking costs $0.60 input / $2.50 output per million tokens (median across 10 API providers). At a 3:1 input-to-output mix that is $1.07 per million tokens, more expensive than 58% of the 360 priced models we track.
What is the context window of Kimi K2 Thinking?
Kimi K2 Thinking accepts up to 262,144 tokens per request and can write up to 262,144 tokens in one response.
How good is Kimi K2 Thinking?
Epoch AI gives Kimi K2 Thinking a Capabilities Index score of 146.0 (likely range 143.4–147.6), ranking it #72 of 148 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 84.2%, OTIS Mock AIME 2024–2025 83.1%.
Is Kimi K2 Thinking open source?
Yes. Moonshot AI publishes the weights, so it can be downloaded and self-hosted.
What inputs does Kimi K2 Thinking support?
Kimi K2 Thinking accepts text and replies in text. It is a reasoning model, supports tool calling.
When was Kimi K2 Thinking released?
Moonshot AI released Kimi K2 Thinking on Nov 6, 2025. Its training data runs to Aug 2024.
What are the best alternatives to Kimi K2 Thinking?
The closest current models from other labs on capability, price and release date are Qwen3.5 Plus (Alibaba (Qwen), ECI 146.8, $0.40 / $2.40), GLM-4.7 (Z.ai (Zhipu), ECI 143.5, $0.60 / $2.20), Nemotron 3 Ultra 550B A55B (NVIDIA, ECI 146.2, $0.50 / $2.50) and GPT-5 Mini (OpenAI, ECI 145.5, $0.25 / $2.00).