Kimi K2
Moonshot's coding-specialist line, with a priced highspeed variant.
Kimi K2 is Moonshot's coding line: K2.7 Code at a 256K context ($0.95 in / $4 out per MTok), a highspeed variant at about 180 tokens per second of output ($1.90/$8), and K2.6 for general work. The one vendor-published output speed in this catalog belongs here.
What it is good at
- Dedicated coding at $0.95 in / $4 out per MTok
- The highspeed variant: about 180 tokens/s of output, up to 260 in short context (vendor-published)
- Cache hits at $0.19 per MTok
What it is less good at
- A 256K context — a quarter of K3's
- No benchmarks published by Moonshot
Reaching it with TeamCLI
- The same Claude Code endpoint route that runs K3 would run the K2 line; no seat has run it yet.
Versions
One block per version, the current one first, each with its own anchor. The comparison table puts the costs and the family's benchmark columns side by side; the values are verbatim, and every one is sourced and dated in its version's section below and in the Sources list. A dash means the source publishes no figure, and nothing here is estimated.
No independent intelligence or speed index is republished here: Artificial Analysis measures both across labs, and its terms allow the link but not the copy — its figures live on its own pages.
| Version | Released | Context | Input price | Output price |
|---|---|---|---|---|
| Kimi K2.7 Code — current | — | 262,144 tokens | $0.95 / MTok (cache miss) | $4.00 / MTok |
| Kimi K2.6 | — | 262,144 tokens | $0.95 / MTok (cache miss) | $4.00 / MTok |
Kimi K2.7 Code — current
- Model id:
kimi-k2.7-code
Abilities
- Released: —
- Context window: 262,144 tokens — Moonshot — Kimi model list (read 2026-10-19).
- Max output: —
- Output speed: Highspeed variant: ~180 tokens/s output, up to 260 in short context — Moonshot — Kimi model list (read 2026-10-19).
- Latency: —
Costs
- Input price: $0.95 / MTok (cache miss) — Moonshot — Kimi pricing (read 2026-10-19). Cache hit $0.19. Highspeed variant: $1.90 in / $8.00 out
- Output price: $4.00 / MTok — Moonshot — Kimi pricing (read 2026-10-19).
Kimi K2.6
- Model id:
kimi-k2.6
Abilities
- Released: —
- Context window: 262,144 tokens — Moonshot — Kimi model list (read 2026-10-19).
- Max output: —
- Output speed: —
- Latency: —
Costs
- Input price: $0.95 / MTok (cache miss) — Moonshot — Kimi pricing (read 2026-10-19). Cache hit $0.16
- Output price: $4.00 / MTok — Moonshot — Kimi pricing (read 2026-10-19).
Sources
- Moonshot — Kimi model list — read 2026-10-19
- Moonshot — Kimi pricing — read 2026-10-19
Figures refreshed 2026-10-19; benchmarks are vendor-reported. Prices are per million tokens unless a figure says otherwise.