MoonshotAI: Kimi K2 0905
Analysis Summary
Kimi K2 0905 is a mid-tier model from MoonshotAI with an intelligence index of 30.9 and a standout agentic index of 48.4, the highest in this batch outside of GPT-5 Codex. It supports tool use and function calling across a 262K context window, making it capable of handling long-document workflows and multi-step agent tasks. GPQA at 0.767 and MMLU Pro at 0.819 reflect solid general reasoning.
For businesses, the strong agentic score makes it a reasonable fit for automated research pipelines, document analysis, and tool-orchestration tasks. Coding capability is more limited at 25.9, so it is not the right choice for software engineering workloads. Instruction following (ifbench 0.417) and long-context reasoning (lcr 0.523) are adequate for structured content tasks.
At $0.60 input and $2.50 output per million tokens, pricing is moderate. Teams needing agentic capability at a lower cost than frontier models will find this a practical option, though the -4 point regional penalty applies given limited enterprise adoption outside its home market.
Assessed June 6, 2026
Editorial notes
Kimi K2 0905 from MoonshotAI offers a strong agentic index of 48.4 and a 262K context window, with solid instruction following and long-context reasoning at competitive pricing.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How MoonshotAI: Kimi K2 0905 compares
MoonshotAI: Kimi K2 0905 ranks #103 of 378 AI models we track for overall intelligence, #106 of 315 for coding, #87 of 289 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 0905
Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does MoonshotAI: Kimi K2 0905 stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
moonshotai/kimi-k2-0905
|
| Provider | moonshotai |
| Release Date | September 4, 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 0905
How much does MoonshotAI: Kimi K2 0905 cost?
MoonshotAI: Kimi K2 0905 costs $0.60 per million input tokens and $2.50 per million output tokens.
What is the context window of MoonshotAI: Kimi K2 0905?
MoonshotAI: Kimi K2 0905 has a context window of 262,144 tokens (262K).
Is MoonshotAI: Kimi K2 0905 good for coding?
On our coding benchmark index, MoonshotAI: Kimi K2 0905 ranks #106 of 315 models, placing it in the broader range of the field for code generation and debugging.
What can MoonshotAI: Kimi K2 0905 do?
MoonshotAI: Kimi K2 0905 supports tool use and function calling.
Who created MoonshotAI: Kimi K2 0905?
MoonshotAI: Kimi K2 0905 is developed by MoonshotAI and was released on September 4, 2025.
