Kimi K3
Language Available Full comparison ↗ moonshot/kimi-k3 · by Moonshot AI
· mixture-of-experts
Pricing — 1 offering(s)
Input tokens
- $3.00 / 1M tokens (input) Current 2026-07-16 → present
Output tokens
- $15.00 / 1M tokens (output) Current 2026-07-16 → present
Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.
See how Kimi K3 fits into a cost-aware routing setup
See how →Capability profile
Coding benchmarks
View the full coding benchmark leaderboard →| Benchmark | Score | Harness | Source |
|---|---|---|---|
| swe-bench-verified ↗ | 93.4% 2026-07 | mini-swe-agent | 📊 leaderboard ↗ |
| terminal-bench-2-1 | 88.3% 2026-07 | kimi-code | 🏢 vendor ↗ |
Operator guidance
Moonshot's current flagship (superseded K2.6, 2026-07-16). Independently confirmed strong on coding (SWE-bench Verified) and now also on reasoning and tool-use (Artificial Analysis Intelligence Index and AA-Briefcase, both #1-2 in class) — the strongest-evidenced entry in the Kimi family. Notably slow output (37.7 tok/s) is the main tradeoff. Drop to Kimi K2.6 for the prior-generation, lower-cost option, or K2.7 Code specifically for coding-focused workloads at a much lower price.
Use cases
- Frontier-scale general and agentic tasks needing a very large context window
- Coding and long-horizon agentic workflows (independently confirmed strong via SWE-bench Verified)
Limitations
- Capability ratings beyond coding/context-window/reasoning/tool-use/speed/cost-efficiency are unknown — no independent benchmark found for instruction-following/multilingual as of the 2026-08-19 SCO-462 sweep
- Full model weights were only committed to a 2026-07-27 release at the time of writing (2026-07-23) — some claims may be preview-stage