Kimi K3 — API Pricing & Benchmarks
Kimi K3 is Moonshot AI's flagship reasoning model, released in 2026-07. The API costs $3.00 per 1M input tokens and $15.0 per 1M output tokens ($6.00 blended at a 3:1 ratio), with cached input at $0.30. It supports a 1.0M-token context window. On the independently measured Artificial Analysis Intelligence Index it scores 59.7, ranking #8 of 68 models tracked on this site, with a median output speed of 38 tokens/sec.
Explore provider routes and additional benchmark sources for Kimi K3
| Provider | Moonshot AI |
| Input price / 1M tokens | $3.00 |
| Output price / 1M tokens | $15.0 |
| Cached input / 1M tokens | $0.30 |
| Blended price (3:1) | $6.00 |
| Context window | 1.0M |
| Max output tokens | 1.0M |
| Knowledge cutoff | — |
| License | open weights |
| Input modalities | T+I+V |
| Output speed (tok/s) | 38 |
| Released | 2026-07 |
| Artificial Analysis Intelligence Index | 59.7 |
| LMArena Elo | 1476 |
| GPQA Diamond | 93.5% |
| SWE-bench Verified | 93.4% |
| Humanity's Last Exam | 46.9% |
| MMMU | 81.6% |
Where Kimi K3 fits
On a blended 3:1 basis Kimi K3 costs $6.00 per 1M tokens, cheaper than 15% of the 80 priced models in this index. As Moonshot AI's flagship it is aimed at the hardest workloads — complex reasoning, agentic coding and multi-step tool use — where output quality dominates cost. Measured output speed of 38 tokens/sec is below the index median of 104 — typical of reasoning-heavy models, and worth checking against interactive latency budgets. The weights are open, so it can be self-hosted for data-residency or cost reasons instead of consumed via API. Cached input is priced at $0.30 (90% below standard input), which rewards prompt structures with long stable prefixes — see our caching guide.
Price history
| Period | Input $/1M | Output $/1M | Cached $/1M |
|---|---|---|---|
| 2026-07-18 → current | $3.00 | $15.0 | $0.30 |
No list-price changes recorded since tracking began. Full dataset: price-history.json (CC BY 4.0).
Alternatives at a similar price
- Claude Sonnet 4.6 (Anthropic) — $6.00/1M blended, AA Index 48.4
- Claude Sonnet 4.5 (Anthropic) — $6.00/1M blended
- GPT-5.4 (OpenAI) — $5.63/1M blended, AA Index 53.1
- GPT-5.3 Codex (OpenAI) — $4.81/1M blended, AA Index 45.5
Compare Kimi K3
About Moonshot AI
Moonshot AI builds the Kimi models. Kimi K3 is currently the strongest open-weights model in this index, benchmarking alongside proprietary flagships while remaining self-hostable.