Kimi K2.6
Language AvailableCompare models
ComparingKimi K2.6with
Pick a model above to see the comparison.
moonshot/kimi-k2.6 · by Moonshot AI · mixture-of-experts
Pricing — 1 offering(s)
Input tokens
- $0.95 / 1M tokens (input) Current 2026-04-20 → present
Output tokens
- $4.00 / 1M tokens (output) Current 2026-04-20 → present
Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.
Capability profile
coding strong
context window strong
reasoning unknown
tool use unknown
instruction following unknown
multilingual unknown
speed unknown
cost efficiency unknown
Coding benchmarks
View full leaderboard →| Benchmark | Score | Harness | Source |
|---|---|---|---|
| swe-bench-verified ↗ | 76.2% 2026-04 | mini-swe-agent | 📊 leaderboard ↗ |
Operator guidance
Moonshot's prior flagship (superseded by K3, 2026-07-16); still status: ga and "the default model for production use" per Moonshot's own docs. Independently confirmed strong on coding via SWE-bench Verified. Step up to K3 for the latest frontier tier, or down to K2.7 Code specifically for coding-focused workloads.
Use cases
- Production agentic and coding workloads at a lower price than the current flagship
- Multi-step agent orchestration (Agent Swarm)
Limitations
- Capability ratings beyond coding/context-window are unknown — no independent benchmark found for reasoning/tool-use/multilingual/speed/cost-efficiency as of this backfill