MoonshotAI: Kimi K2.5
Analysis Summary
MoonshotAI Kimi K2.5 is a mid-tier model with an intelligence index of 29.4 and an agentic index of 50.1. Vision support and a 262K context window add practical breadth, and the tau2 of 0.813 indicates reasonable reliability on structured multi-step tasks. GPQA (0.789) is strong for its intelligence tier, suggesting above-average performance on knowledge-intensive questions. Instruction following (ifbench 0.437) is below average, which is a limitation for structured output tasks.
For businesses, Kimi K2.5 suits mid-complexity workflows: visual content analysis, long-document summarisation, and tool-use pipelines where cost is a consideration. The weak instruction-following score means it is less reliable for tasks requiring precise structured outputs or strict format adherence.
At $0.375 input and $2.025 output, pricing is moderate. A -4 point regional penalty applies given MoonshotAI's limited enterprise adoption. Teams should verify API availability and test instruction-following quality on their specific use case before production deployment.
Assessed June 30, 2026
Editorial notes
MoonshotAI Kimi K2.5 delivers an intelligence index of 29.4 with vision support, tool use, and a 262K context window; tau2 of 0.813 confirms reasonable multi-step reliability at a mid-range price point.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How MoonshotAI: Kimi K2.5 compares
MoonshotAI: Kimi K2.5 ranks #84 of 385 AI models we track for overall intelligence, #89 of 293 for agentic tasks. Its 262K-token context window is larger than 81% of the models we list. At $0.38 per million input tokens it is cheaper than 39% of comparable models.
About MoonshotAI: Kimi K2.5
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed..
Capabilities
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does MoonshotAI: Kimi K2.5 stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
moonshotai/kimi-k2.5
|
| Provider | moonshotai |
| Release Date | January 27, 2026 |
| Context Length | 262,144 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.38 | $0.000375 |
| Output | $2.03 | $0.002025 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about MoonshotAI: Kimi K2.5
How much does MoonshotAI: Kimi K2.5 cost?
MoonshotAI: Kimi K2.5 costs $0.38 per million input tokens and $2.03 per million output tokens.
What is the context window of MoonshotAI: Kimi K2.5?
MoonshotAI: Kimi K2.5 has a context window of 262,144 tokens (262K).
What can MoonshotAI: Kimi K2.5 do?
MoonshotAI: Kimi K2.5 supports image/vision input, tool use, and function calling.
Who created MoonshotAI: Kimi K2.5?
MoonshotAI: Kimi K2.5 is developed by MoonshotAI and was released on January 27, 2026.
