MoonshotAI: Kimi K2 0905 (exacto)
Analysis Summary
Kimi K2 0905 (exacto) is a variant of MoonshotAI's Kimi K2 family, offering a 262K context window with tool use and function calling. No benchmark data has been published for this specific variant, making it impossible to assess reasoning, coding, or agentic capability against the broader field.
For businesses, the large context window is a practical asset if the underlying model capability is strong, but without benchmark evidence there is no basis for recommending it over the well-benchmarked Kimi K2.6, which has demonstrated competitive intelligence and agentic scores. The pricing at $0.60/1M input and $2.50/1M output is mid-range.
This variant should be treated as experimental until independent benchmark results are available. Teams already using the Kimi K2 family may evaluate it for specific use cases, but it cannot be recommended for primary business deployment at this stage.
Assessed June 6, 2026
Editorial notes
Kimi K2 0905 (exacto) from MoonshotAI has no benchmark data available; tool use and function calling are supported with a 262K context window, but capability cannot be assessed without evidence.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How MoonshotAI: Kimi K2 0905 (exacto) compares
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 (exacto)
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 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k. This update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.
Capabilities
How does MoonshotAI: Kimi K2 0905 (exacto) stack up?
Compare side-by-side with other legacy models.
Model Information
| OpenRouter ID |
moonshotai/kimi-k2-0905:exacto
|
| Provider | moonshotai |
| Release Date | September 4, 2025 |
| Context Length | 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.
External Resources
Frequently asked questions about MoonshotAI: Kimi K2 0905 (exacto)
How much does MoonshotAI: Kimi K2 0905 (exacto) cost?
MoonshotAI: Kimi K2 0905 (exacto) costs $0.60 per million input tokens and $2.50 per million output tokens.
What is the context window of MoonshotAI: Kimi K2 0905 (exacto)?
MoonshotAI: Kimi K2 0905 (exacto) has a context window of 262,144 tokens (262K).
What can MoonshotAI: Kimi K2 0905 (exacto) do?
MoonshotAI: Kimi K2 0905 (exacto) supports tool use and function calling.
Who created MoonshotAI: Kimi K2 0905 (exacto)?
MoonshotAI: Kimi K2 0905 (exacto) is developed by MoonshotAI and was released on September 4, 2025.
