Moonshot AI
Kimi K3
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
Model facts
- Context window
- 1.05M tokens
- Maximum output
- 131K tokens
- Cheapest paid input
- $2 per 1M tokens
- Cheapest paid output
- $8 per 1M tokens
- Open weights
- yes
- Providers
- 71
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image, video, pdf.
Local hardware estimate
At 4K context: Q4_K_M 1702.4 GiB, Q8_0 2996.9 GiB, F16 5424.1 GiB working memory.
- Parameters
- 2779.9 billion
- Architecture
- kimik3
- Model license
- other
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| max | 59.7 | 76.2 | not measured | 37.9 |
| low | 48.3 | 72.0 | not measured | 33.7 |
Observed price history
- 2026-08-24: $2 input / $8 output per 1M tokens
API providers
- Kenari — model id kimi-k3; free input / free output per 1M tokens; provider documentation
- Kimi For Coding — model id k3; free input / free output per 1M tokens; provider documentation
- Nvidia — model id moonshotai/kimi-k3; free input / free output per 1M tokens; provider documentation
- SCNet Token Plan — model id Kimi-K3; free input / free output per 1M tokens; provider documentation
- Umans AI Coding Plan — model id umans-kimi-k3; free input / free output per 1M tokens; provider documentation
- ZenMux (Free) — model id moonshotai/kimi-k3-free; free input / free output per 1M tokens; provider documentation
- CrofAI — model id kimi-k3; $2 input / $8 output per 1M tokens; provider documentation
- NanoGPT — model id moonshotai/kimi-k3; $2 input / $10 output per 1M tokens; provider documentation
- Requesty — model id kimi-k3; $2.25 input / $11.25 output per 1M tokens; provider documentation
- Requesty (EU) — model id kimi-k3@eu; $2.25 input / $11.25 output per 1M tokens; provider documentation
- Vancine — model id kimi-k3; $2.4 input / $12 output per 1M tokens; provider documentation
- ai& — model id moonshotai/kimi-k3; $3 input / $12.5 output per 1M tokens; provider documentation
- Merge Gateway — model id moonshot/kimi-k3; $2.9 input / $14 output per 1M tokens; provider documentation
- DevPass (LLM Gateway) — model id kimi-k3; $2.83 input / $14.13 output per 1M tokens; provider documentation
- LLM Gateway (SCX.ai) — model id scx-ai-gp/kimi-k3; $2.83 input / $14.13 output per 1M tokens; provider documentation
- Deep Infra — model id moonshotai/Kimi-K3; $2.85 input / $14.25 output per 1M tokens; provider documentation
- DigitalOcean — model id kimi-k3; $2.85 input / $14.25 output per 1M tokens; provider documentation
- Cortecs — model id kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- AIHubMix — model id kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Abacus — model id moonshotai/Kimi-K3; $3 input / $15 output per 1M tokens; provider documentation
- Arcee — model id moonshotai/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Baseten — model id moonshotai/Kimi-K3; $3 input / $15 output per 1M tokens; provider documentation
- Berget.AI — model id moonshotai/Kimi-K3; $3 input / $15 output per 1M tokens; provider documentation
- ClinePass — model id cline-pass/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Cloudflare AI Gateway — model id moonshotai/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- CoralBricks — model id kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- CrossModel — model id moonshot/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Eden AI — model id moonshot/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- EmpirioLabs AI — model id kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Fireworks AI — model id accounts/fireworks/models/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- GitHub Copilot — model id kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Hugging Face — model id moonshotai/Kimi-K3; $3 input / $15 output per 1M tokens; provider documentation
- Impossibl — model id moonshotai/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Jalapeno Cloud — model id Kimi-K3; $3 input / $15 output per 1M tokens; provider documentation
- Kilo Gateway — model id moonshotai/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- LLM Gateway (CanopyWave) — model id canopywave/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- LLM Gateway (Fireworks AI) — model id fireworks/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- LLM Gateway (Moonshot AI) — model id moonshot/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- LLM Gateway (NovitaAI) — model id novita/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- LLM Gateway (Together AI) — model id together-ai/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Modal — model id moonshotai/Kimi-K3; $3 input / $15 output per 1M tokens; provider documentation
- Moonshot AI — model id kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Moonshot AI (China) — model id kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Nebius Token Factory — model id moonshotai/Kimi-K3; $3 input / $15 output per 1M tokens; provider documentation
- Neon — model id kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Neuralwatt — model id kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- NovitaAI — model id moonshotai/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Ofox — model id moonshotai/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- OpenCode Go — model id kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- OpenCode Zen — model id kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- OpenRouter — model id moonshotai/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- OpenRouter (batch) — model id moonshotai/kimi-k3:batch; $3 input / $15 output per 1M tokens; provider documentation
- Opper — model id moonshot/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Perplexity Agent — model id moonshot-ai/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Pioneer — model id moonshotai/Kimi-K3; $3 input / $15 output per 1M tokens; provider documentation
- Synthetic — model id hf:moonshotai/Kimi-K3; $3 input / $15 output per 1M tokens; provider documentation
- TensorX — model id moonshotai/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Together AI — model id moonshotai/Kimi-K3; $3 input / $15 output per 1M tokens; provider documentation
- TokenGo — model id moonshotai/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Umans AI — model id umans-kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Vercel AI Gateway — model id moonshotai/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Vivgrid — model id kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- ZenMux — model id moonshotai/kimi-k3; $3 input / $15 output per 1M tokens; provider documentation
- Charm Hyper — model id kimi-k3; $3.27 input / $16.33 output per 1M tokens; provider documentation
- OrcaRouter — model id kimi/kimi-k3; $3.3 input / $16.5 output per 1M tokens; provider documentation
- Venice AI — model id kimi-k3; $3.75 input / $18.75 output per 1M tokens; provider documentation
- GreenPT — model id kimi-k3; $3.76 input / $18.81 output per 1M tokens; provider documentation
- Tinfoil — model id kimi-k3; $4 input / $20 output per 1M tokens; provider documentation
- DevPass (LLM Gateway) — model id kimi-k3-fast; $4.5 input / $22.5 output per 1M tokens; provider documentation
- Arena — model id kimi-k3; not published input / not published output per 1M tokens; provider documentation
- Ollama Cloud — model id kimi-k3; not published input / not published output per 1M tokens; provider documentation