Model
Kimi K2.6
Multimodal Kimi workhorse for agent loops, coding tasks, and visual context
Compare providers (sorted by listed input price)
62 of 67 providers publish a price for Kimi K2.6. The cheapest full-context option is Vultr at $0.3/$1.2 per M — 67% below Moonshot AI's own price. routing.run lists lower but caps context at 200K.
Best price history
Daily lowest published price across live providers. A lower line is better for the buyer.
- Best input /M
- $0.275▲ 25.0%
- Best output /M
- $1.10▼ 3.3%
- Provider coverage
- 75
- 78 at the start · 24 snapshots
Price badge
https://www.vaanalytics.in/badge/moonshotai/kimi-k2.6.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Recent changes
Changelog →- new modelvia llmgateway-providers · Sep 13, 2026
- repricedvia llmgateway · Sep 9, 2026
- input: $0.22 → $0.6
- output: $1.14 → $3.05
- cache_read: $0.048 → $0.13
- new modelvia 302ai · Sep 9, 2026
- contextvia cortecs · Sep 2, 2026
- output: 256K → 262K tokens
- repricedvia inceptron · Aug 28, 2026
- input: $0.54 → $0.53
- cache_read: $0.15 → $0.17
- new providervia tokengo · Aug 28, 2026
Benchmarks
- SWE-Bench Verified ↗(resolved)report ↗Unclassified source80.2
- Artificial Analysis Coding Agent Index ↗(average pass@1)report ↗Independent50.5
- SWE-Atlas Codebase QnA(pass@1)report ↗Independent59.8
- SWE-Bench Pro ↗(pass@1)report ↗Independent27.3
- Terminal-Bench ↗(pass@1)report ↗Independent64.3
Scores a lab published about its own model are claims, not measurements. Rankings elsewhere on this site use independently measured scores only.
Weights
No machine-readable licence on the model card. Check it before you rely on this. Weights download without an access request.
licence and gating from the Hugging Face model card ↗ — the card is authoritative, this is a summary
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.