MoonshotAI: Kimi K2 0905

Kimi K2 0905 is a text-only model from MoonshotAI with a context window of 262,144 tokens and a matching maximum output length, making it suited for tasks that require processing or generating very long documents. It supports tool use, does not include a built-in reasoning mode, and has no confirmed structured output support. Input is priced at $0.60 per million tokens and output at $2.50 per million tokens. The long context ceiling is the clearest reason to shortlist this model, particularly for workflows involving large codebases, lengthy transcripts, or extended document analysis where smaller windows create problems. The pricing is moderate, sitting below several frontier competitors on input cost. That said, benchmark coverage is currently zero, meaning there is no independent performance data to anchor quality expectations, so teams considering Kimi K2 0905 should plan for their own evaluation before committing to production use.