tokenstat
tokenstat
Moonshot AI

Moonshot: Kimi K3

moonshot/kimi-k3 · rates as of · list price from platform.kimi.ai · How this catalog is built · Benchmarks

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

List input
$3
$/MTok · Moonshot AI
List output
$15
$/MTok
Context
1.1M
tokens
Sources
4
95 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↑ higherInput $0.192 → $0.2
  • ↑ higherOutput $7.15 → $15
  • ↑ higherInput $0.1495 → $0.192
  • ↓ lowerOutput $15 → $7.15
  • ↓ lowerInput $0.192 → $0.1495
  • ↑ higherOutput $10.80 → $15
  • ↓ lowerInput $0.239 → $0.192
  • ↓ lowerOutput $20 → $10.80

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (5 omitted). Show free/$0 listings.

SourceProviderInputOutputCache readContext
tokenstatmoonshotai/kimi-k3Moonshot AI$3$15$0.31.0M
models.devcheapestmoonshotai/kimi-k3OpenRouter$0.2$15$0.191.0M
OpenRoutermoonshotai/kimi-k3OpenRouter$0.2$16$0.191.0M
models.devmoonshotai/kimi-k3NanoGPT$0.45$9.60$0.131.0M
models.devkimi-k3Kenari$0.8571$8.57$0.11431.0M
models.devkimi-k3Engy$1.95$9.75$0.1951.1M
models.devKimi-K3Ainetcafe$2.10$10.50$0.3262K
OpenRoutermoonshotai/kimi-k3:batchOpenRouter$2.28$11.40$0.2281.0M
models.devkimi-k3Boundless$2.30$11.40$0.231.0M
models.devmoonshotai/kimi-k3IteraCompute$2.35$11.76$0.231.0M
models.devkimi-k3Vancine$2.40$12$0.241.0M
LiteLLMKimi-K3N/A$2.50$12.50$0.25N/A
LiteLLMsail/moonshotai/Kimi-K3N/A$2.50$12.50$0.25N/A
models.devmoonshotai/Kimi-K3SiliconFlow$2.70$13.50$0.271.0M
models.devmoonshotai/kimi-k3Wallaby$2.70$13.50$0.271.0M
models.devkimi-k3Alibaba / Qwen$2.83$14.13$0.2831.0M
LiteLLMscx-ai/Kimi-K3N/A$2.83$14.13$0.28N/A
models.devmoonshotai/Kimi-K3DeepInfra$2.85$14.25$0.2851.0M
models.devkimi-k3Moonshot AI (China)$2.99$14.94$0.29881.0M
LiteLLMdatabricks-kimi-k3N/A$3$15$0.3N/A
LiteLLMdatabricks/databricks-kimi-k3N/A$3$15$0.3N/A
models.devmoonshotai/kimi-k3Ai&$3$12.50$0.51.0M
models.devkimi-k3Cortecs$3$15$01.0M
models.devmoonshotai/Kimi-K3Abacus$3$15$0.31.0M
models.devmoonshotai/kimi-k3Arcee$3$15$0.31.0M
models.devmoonshotai/Kimi-K3Baseten$3$15$0.31.0M
models.devmoonshotai/kimi-k3Cloudflare$3$15$0.31.0M
models.devmoonshotai/Kimi-K3CommandCode$3$15$0.31M
models.devmoonshotai/Kimi-K3Hugging Face$3$15$01M
models.devmoonshotai/kimi-k3Impossibl$3$15$0.31.0M
models.devmoonshotai/kimi-k3Kilo Gateway$3$15$0.31.0M
models.devmoonshotai/Kimi-K3Modal$3$15$0.31.0M
models.devkimi-k3Moonshot AI$3$15$0.31.0M
models.devmoonshotai/Kimi-K3Nebius$3$15$0.31.0M
models.devmoonshotai/kimi-k3Novita AI$3$15$0.31.0M
models.devmoonshotai/kimi-k3Ofox$3$15$0.31.0M
models.devmoonshotai/Kimi-K3Pioneer$3$15$0.31M
models.devmoonshotai/kimi-k3Standard Compute$3$15$0.31.0M
models.devmoonshotai/kimi-k3TensorX$3$15$0.751.0M
models.devmoonshotai/Kimi-K3Together AI$3$15$0.31.0M
models.devmoonshotai/kimi-k3TokenGo$3$15$0.31.0M
models.devmoonshotai/kimi-k3Vercel AI Gateway$3$15$0.31M
models.devmoonshotai/kimi-k3ZenMux$3$15$0.31.0M
models.devkimi-k3302.AI$3$15$0.31.0M
models.devkimi-k3AIHubMix$3$15$0.31.0M
models.devkimi-k3Alibaba / Qwen$3$15$0.31.0M
models.devkimi-k3DigitalOcean$3$15$0.31.0M
models.devkimi-k3EmpirioLabs AI$3$15$31.0M
models.devkimi-k3GitHub Copilot$3$15$0.31.0M
models.devKimi-K3Jalapeno Cloud$3$15$0.31.0M
models.devaws-bedrock/kimi-k3LLM Gateway$3$15$0.31.0M
models.devkimi-k3DevPass (LLM Gateway)$3$15$0.31.0M
models.devkimi-k3Moark$3$15$01.0M
models.devkimi-k3Neon$3$15$0.31.0M
models.devkimi-k3Neuralwatt$3$15$0.31.0M
models.devkimi-k3Ollama Cloud$3$15$0.31.0M
models.devkimi-k3OpenCode Go$3$15$0.31.0M
models.devkimi-k3OpenCode$3$15$0.31.0M
models.devkimi-k3Opper$3$15$01.0M
models.devkimi-k3Requesty$3$15$0.451.0M
models.devkimi-k3Vivgrid$3$15$0.31M
models.devkimi-k3Wally$3$15$0.31.0M
models.devmoonshot/kimi-k3AI/ML API$3$15$0.31.0M
models.devmoonshot/kimi-k3CrossModel$3$15$0.31.0M
models.devmoonshot/kimi-k3Eden AI$3$15$0.31.0M
models.devmoonshot/kimi-k3Merge Gateway$3$15$0.31.0M
models.devmoonshot/kimi-k3Tempr Gateway$3$15$0.31.0M
models.devglobal.moonshotai.kimi-k3Amazon Bedrock$3$15$0.31.0M
models.devcline-pass/kimi-k3ClinePass$3$15$0.31.0M
models.devaccounts/fireworks/models/kimi-k3Fireworks AI$3$15$0.31.0M
models.devTEE/kimi-k3NanoGPT$3$15$1.501.0M
models.devkimi/kimi-k3OrcaRouter$3$15$0.31.0M
models.devmoonshot-ai/kimi-k3Perplexity$3$15$0.31.0M
models.devhf:moonshotai/Kimi-K3Synthetic$3$15$0.45524K
models.devumans-kimi-k3Umans AI$3$15$0.31.0M
LiteLLMkimi-k3N/A$3$15$0.3N/A
LiteLLMtencent/kimi-k3N/A$3$15$0.3N/A
LiteLLMmoonshot/kimi-k3N/A$3$15$0.3N/A
LiteLLMglobal.moonshotai.kimi-k3N/A$3$15$0.3N/A
LiteLLMaccounts/fireworks/models/kimi-k3N/A$3$15$0.3N/A
LiteLLMperplexity/perplexity/kimi-k3N/A$3$15$0.3N/A
LiteLLMnovita/moonshotai/kimi-k3N/A$3$15$0.3N/A
LiteLLMkyma/kimi-k3N/A$3.05$15.26$0.405N/A
models.devscx-ai-gp/kimi-k3LLM Gateway$3.13$15.68$0.3191.0M
models.devkimi-k3Melious$3.18$15.89$0.79161M
models.devkimi-k3Charm Hyper$3.27$16.33$0.32661.0M
models.devmoonshotai/kimi-k3NEAR AI Cloud$3.30$16.50$0.331.0M
models.devus.moonshotai.kimi-k3Amazon Bedrock$3.30$16.50$0.331.0M
LiteLLMus.moonshotai.kimi-k3N/A$3.30$16.50$0.33N/A
LiteLLMmoonshotai.kimi-k3N/A$3.30$16.50$0.33N/A
models.devmoonshotai/Kimi-K3Berget.AI$3.36$16.82$1.01328K
models.devmoonshotai/kimi-k3Prime Inference$3.45$17.25$01.0M
models.devkimi-k3Venice AI$3.75$18.75$0.3751M
models.devkimi-k3GreenPT$3.76$18.81$0.94051.0M
models.devkimi-k3Tinfoil$4$20$0.6262K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: image
  • In: video
  • In: pdf
  • Out: text
Released: 2026-07-16Output limit: 944K tokensFamily: kimi-k3

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

See what this model costs you

The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.

macOSDownloadWindowsPreviewCLImacOS · Linux · WindowsApp StoreDownloadGoogle PlayDownload