Skip to content

Model

Kimi K2 Thinking

Thinking Kimi model for slower research passes, planning, and hard technical questions

18 providers · 18 listingsreleased knowledge cutoff 2024-08open weights
$0.47
lowest input /M · Vercel AI Gateway
$2
lowest output /M · Vercel AI Gateway
262K
context window
262K
max output

Compare providers (sorted by listed input price)

16 of 18 providers publish a price for Kimi K2 Thinking. The cheapest full-context option is Helicone at $0.48/$2 per M. Vercel AI Gateway lists lower but caps context at 216K.

22 listings
Cache read /MCache write /MCapabilitiesStatus
OpenCode Zen
kimi-k2-thinking
$0.4$2.50$0.4262Kreasoningtoolsno structuredno visiondeprecatedSep 5, 2025
Vercel AI Gateway
moonshotai/kimi-k2-thinking
$0.47$2$0.141216Kreasoningtoolsno structuredno visionNov 6, 2025
Helicone
kimi-k2-thinking
$0.48$2256Kno reasoningtoolsno structuredno visionNov 6, 2025
IO.NET
moonshotai/Kimi-K2-Thinking
$0.55$2.25$0.275$1.1033Kreasoningtoolsno structuredno visionNov 1, 2024
Alibaba (China)
kimi-k2-thinking
$0.574$2.29262Kreasoningtoolsstructuredno visionNov 6, 2025
302.AI
kimi-k2-thinking
$0.575$2.30262Kreasoningtoolsno structuredno visionSep 5, 2025
NanoGPT
moonshotai/kimi-k2-thinking
$0.6$2.50$0.15262Kreasoningtoolsstructuredno visionNov 6, 2025
LLM Gateway
vertex-openai/kimi-k2-thinking
$0.6$2.50$0.06262Kreasoningtoolsno structuredno visionNov 6, 2025
NovitaAI
moonshotai/kimi-k2-thinking
$0.6$2.50$0.15262Kreasoningtoolsstructuredno visionJun 29, 2026
Charm Hyper
kimi-k2-thinking
$0.6$2.50$0.3262Kreasoningtoolsno structuredno visionSep 2, 2026
Hugging Face
moonshotai/Kimi-K2-Thinking
$0.6$2.50$0.15262Kreasoningtoolsno structuredno visionNov 6, 2025
DevPass (LLM Gateway)
kimi-k2-thinking
$0.6$2.50$0.06262Kreasoningtoolsno structuredno visionNov 6, 2025
Kilo Gateway
moonshotai/kimi-k2-thinking
$0.6$2.50$0.15262Kreasoningtoolsstructuredno visionNov 6, 2025
Amazon Bedrock
moonshot.kimi-k2-thinking
$0.6$2.50262Kreasoningtoolsstructuredno visionDec 2, 2025
OpenRouter
moonshotai/kimi-k2-thinking
$0.6$2.50$0.15262Kreasoningtoolsstructuredno visionNov 6, 2025
Meganova
moonshotai/Kimi-K2-Thinking
$0.6$2.60262Kreasoningtoolsno structuredno visionNov 6, 2025
Eden AI
amazon/moonshot.kimi-k2-thinking
$0.6$2.50128Kreasoningno toolsno structuredno visionNov 6, 2025
Vertex
moonshotai/kimi-k2-thinking-maas
$0.6$2.50$0.06262Kreasoningtoolsstructuredno visiondeprecatedNov 13, 2025
Merge Gateway
moonshotai/kimi-k2-thinking
$0.6$2.50262Kreasoningtoolsno structuredno visiondeprecatedNov 6, 2025
ZenMux
moonshotai/kimi-k2-thinking
$0.6$2.50$0.15262Kreasoningtoolsno structuredno visiondeprecatedNov 6, 2025

Best price history

Daily lowest published price across live providers. A lower line is better for the buyer.

Best input /M
$0.47unchanged
Best output /M
$2unchanged
Provider coverage
18
19 at the start · 24 snapshots

Published best prices are unchanged.

24 daily snapshots collected from Aug 21, 2026 through Sep 14, 2026. A price chart will appear after the first real move.

Price badge

Current price badge for Kimi K2 Thinking
![Kimi K2 Thinking price](https://www.vaanalytics.in/badge/moonshotai/kimi-k2-thinking.svg)
https://www.vaanalytics.in/badge/moonshotai/kimi-k2-thinking.svg

Live 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 →
  • contextvia openrouter · Sep 13, 2026
    • output: 100K → 98K tokens
  • contextvia kilo · Sep 13, 2026
    • output: 100K → 98K tokens
  • capabilityvia amazon-bedrock · Sep 13, 2026
    • description: Kimi reasoning model for long-horizon research, planning, and tool use → Thinking Kimi model for slower research passes, planning, and hard technical questions
    • knowledge: — → 2024-08
    • release_date: 2025-12-02 → 2025-11-06
  • repricedvia hyper · Sep 11, 2026
    • cache_read: — → $0.3
    • cache_write: $0.3 → —
  • contextvia kilo · Sep 10, 2026
    • output: 236K → 100K tokens
  • repricedvia openrouter · Sep 10, 2026
    • output: 236K → 100K tokens
    • cache_read: — → $0.15

Benchmarks

Scores a lab published about its own model are claims, not measurements. Rankings elsewhere on this site use independently measured scores only.

Weights

Licence unclearother1.03T params

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.