MoonshotAI: Kimi K2 Thinking
Analysis Summary
Kimi K2 Thinking is MoonshotAI's reasoning-focused model with an intelligence index of 32.7 and standout coding performance: LiveCodeBench at 0.853 and SciCode at 0.424 place it among the stronger coding models in the field. Its agentic index of 62.0 and TAU2 of 0.930 confirm reliable multi-step execution, and tool use plus function calling are supported across a 262K context window.
For businesses, this model suits autonomous coding agents, complex technical problem-solving, and long-document analysis. GPQA at 0.838 and MMLU Pro at 0.848 indicate strong general reasoning, and long-context reliability (LCR 0.663) supports extended workflows. The main limitation is the absence of vision support, restricting it to text-only pipelines.
At $0.60 input and $2.50 output per million tokens, pricing is reasonable for its capability level. Teams needing a strong coding and agentic model at below-frontier cost will find K2 Thinking competitive, though MoonshotAI's enterprise support footprint is smaller than major providers.
Assessed June 30, 2026
Editorial notes
Kimi K2 Thinking from MoonshotAI pairs strong coding and agentic performance with a 262K context window and tool use, delivering frontier-adjacent results at moderate pricing for technical workflows.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How MoonshotAI: Kimi K2 Thinking compares
MoonshotAI: Kimi K2 Thinking ranks #68 of 385 AI models we track for overall intelligence, #57 of 293 for agentic tasks. Its 262K-token context window is larger than 81% of the models we list. At $0.60 per million input tokens it is cheaper than 32% of comparable models.
About MoonshotAI: Kimi K2 Thinking
Kimi K2 Thinking is Moonshot AIās 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..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does MoonshotAI: Kimi K2 Thinking stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
moonshotai/kimi-k2-thinking
|
| Provider | moonshotai |
| Release Date | November 6, 2025 |
| Context Length | 262,144 tokens |
| Max Completion | 262,144 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.60 | $0.000600 |
| Output | $2.50 | $0.002500 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about MoonshotAI: Kimi K2 Thinking
How much does MoonshotAI: Kimi K2 Thinking cost?
MoonshotAI: Kimi K2 Thinking costs $0.60 per million input tokens and $2.50 per million output tokens.
What is the context window of MoonshotAI: Kimi K2 Thinking?
MoonshotAI: Kimi K2 Thinking has a context window of 262,144 tokens (262K).
What can MoonshotAI: Kimi K2 Thinking do?
MoonshotAI: Kimi K2 Thinking supports tool use and function calling.
Who created MoonshotAI: Kimi K2 Thinking?
MoonshotAI: Kimi K2 Thinking is developed by MoonshotAI and was released on November 6, 2025.
