Moonshot AI
Kimi K2 Thinking
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.
At a glance
- Input / 1M
- $0.60
- Output / 1M
- $2.50
- Context
- 262K
- Max output
- 98K
- Intelligence
- 22
- Released
- Nov 2025
Pricing
Kimi K2 Thinking API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.60 |
|---|---|
| Output tokensPer 1M tokens | $2.50 |
| Cached input (read)Per 1M tokens | $0.15 |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$2.45
per 1,000 requests
Coding task
30K in, 4K out
$28
per 1,000 requests
Long document summary
150K in, 2K out
$95
per 1,000 requests
Benchmarks
Kimi K2 Thinking benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
22
Coding index
Not available
Agentic index
Not available
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 262K tokens
- Max output
- 98K tokens
- Input types
- Text
- Output types
- Text
- Reasoning effort
- Not available
- Release date
- November 6, 2025
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
Kimi K2 Thinking vs other models
See how Kimi K2 Thinking stacks up head to head on price, benchmarks, and features.
Kimi K2 Thinking vs Kimi K2.6
Moonshot AI vs Moonshot AI
See comparisonKimi K2 Thinking vs Kimi K2.7 Code
Moonshot AI vs Moonshot AI
See comparison
Kimi K2 Thinking vs DeepSeek V4 Flash 0423
Moonshot AI vs DeepSeek
See comparisonKimi K2 Thinking vs Kimi K2.5
Moonshot AI vs Moonshot AI
See comparisonKimi K2 Thinking vs Nemotron 3 Ultra
Moonshot AI vs NVIDIA
See comparison
Kimi K2 Thinking vs Qwen3.5-27B
Moonshot AI vs Qwen
See comparisonAlternatives
Kimi K2 Thinking alternatives
Similar models worth considering, and where each one has the edge.
Moonshot AI
Kimi K2.6
Moonshot AI
Kimi K2.7 Code
DeepSeek
DeepSeek V4 Flash 0423
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does Kimi K2 Thinking cost?
Kimi K2 Thinking costs $0.60 per 1M input tokens and $2.50 per 1M output tokens through the API. A typical chat message costs about $2.45 per 1,000 messages.
What is the context window of Kimi K2 Thinking?
Kimi K2 Thinking accepts up to 262K tokens of input and can write up to 98K tokens in a single response.
What is the best alternative to Kimi K2 Thinking?
Kimi K2.6 from Moonshot AI is a strong alternative. It offers: 1.0x cheaper output, higher intelligence score, accepts image.
Can I use Kimi K2 Thinking alongside other models?
Yes. Shortcut Chat sends one prompt to Kimi K2 Thinking and any other models you pick at the same time, so you can compare answers side by side.
Try Kimi K2 Thinking next to every other model.
Use Kimi K2 Thinking alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.