MoonshotAI: Kimi K2 0711
Analysis Summary
MoonshotAI: Kimi K2 0711 sits in the Specialist tier on our leaderboard, ranked #123 of 544 published models on overall intelligence. At $0.570 input and $2.30 output per 1M tokens, it is among the most expensive on the market. It offers a standard large context window and supports tool use, function calling, and reasoning.
Editorial notes
Kimi K2 0711 from MoonshotAI shows solid agentic and livecodebench scores with tool use and function calling at moderate pricing; the -4 point regional penalty applies, and intelligence index sits in the good range.
Assessed May 5, 2026
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does MoonshotAI: Kimi K2 0711 stack up?
Compare side-by-side with other specialist models.
Model Information
| OpenRouter ID |
moonshotai/kimi-k2
|
| Provider | moonshotai |
| Release Date | July 11, 2025 |
| Context Length | 131,072 tokens |
| Max Completion | 32,768 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.57 | $0.000570 |
| Output | $2.30 | $0.002300 |
Live Performance
Live endpoint metrics ā refreshed every 30 minutes.
