Kimi AI Models
Moonshot AI with exceptional long-form document processing and analysis.
4 active modelsAvailable Models
$2.80 / $14.00 per 1M
$0.90 / $3.75 per 1M
$0.90 / $3.80 per 1M
$0.56 / $2.95 per 1M
About Kimi Models
Usage patterns
Kimi leans into reasoning and math, with 4 active variants priced $0.56–$2.80/1M input. The reasoning-tuned models suit multi-step logic and STEM tasks; use the lighter variants for throughput where step-by-step thinking isn't required.
Pricing across the lineup
Input pricing varies 80% across the lineup ($0.56 → $2.80/1M). At 1M requests/month with ~1K input tokens, the cheapest variant costs roughly $0.56 while the flagship runs $2.80 — a 80% gap that compounds fast at scale. Output-token pricing follows the same tiering, so long-form generation amplifies the difference.
Provider notes
Kimi sits in the General Purpose category. Moonshot AI with exceptional long-form document processing and analysis. The 1M maximum context window (on Kimi K3) is the largest in this lineup — enough to ingest entire codebases or long documents in one call.
Where Kimi fits
Real-world fit: Kimi variants are commonly used for code-completion copilots, automated refactoring pipelines, and test generation at scale. The cheaper coding variants handle bulk linting/fixing; the flagship is reserved for architectural changes and complex bug fixes.