MoonshotAI: Kimi K2 0711
Analysis Summary
MoonshotAI: Kimi K2 0711 sits in the Specialist tier on our leaderboard, ranked #133 of 557 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 a solid agentic index and tool use support at moderate pricing, but intelligence and coding indices are below the competitive midfield; -4 penalty applied for provider accessibility.
Assessed May 14, 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.
