Kimi K3
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.
- Organization
- Moonshot AI
- Family
- kimi-k3
- Providers
- 76
- Context
- 1,048,576
- Output limit
- 131,072
- Knowledge
- —
- Release
- 2026-07-16
- Updated
- 2026-07-16
- Weights
- Open
- Input
- text, image, video
- Output
- text
- Capabilities
- Tools, Reasoning, Structured
Providers
Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.
| Provider | Model ID | Context | Output | Input / output · 1M | Reasoning | Tools | Structured | Details |
|---|---|---|---|---|---|---|---|---|
| 302.AI | kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Abacus | moonshotai/Kimi-K3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| ai& | moonshotai/kimi-k3 | 1,048,576 | 131,072 | $3.00 / $12.50 | Yes | Yes | Yes | View |
| AIHubMix | kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| ainetcafe | Kimi-K3 | 262,144 | 32,768 | $2.10 / $10.50 | Yes | Yes | Yes | View |
| Alibaba | kimi-k3 | 1,048,576 | 1,048,576 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Alibaba (China) | kimi-k3 | 1,048,576 | 1,048,576 | $2.827 / $14.133 | Yes | Yes | Yes | View |
| Amazon Bedrock | us.moonshotai.kimi-k3 | 1,048,576 | 128,000 | $3.30 / $16.50 | Yes | Yes | Yes | View |
| Amazon Bedrock | global.moonshotai.kimi-k3 | 1,048,576 | 128,000 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Arcee | moonshotai/kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Baseten | moonshotai/Kimi-K3 | 1,048,576 | 262,144 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Berget.AI | moonshotai/Kimi-K3 | 327,680 | 32,768 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Charm Hyper | kimi-k3 | 1,048,576 | 16,000 | $3.2664 / $16.332 | Yes | Yes | Yes | View |
| Chutes | moonshotai/Kimi-K3-TEE | 1,048,576 | 65,535 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| ClinePass | cline-pass/kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Cloudflare AI Gateway | moonshotai/kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Cortecs | kimi-k3 | 1,048,576 | 1,048,576 | $3.00 / $14.999 | Yes | Yes | Yes | View |
| CrofAI | kimi-k3-eco | 1,000,000 | 131,072 | $1.00 / $4.00 | Yes | Yes | Yes | View |
| CrofAI | kimi-k3 | 1,000,000 | 262,144 | $2.00 / $8.00 | Yes | Yes | Yes | View |
| CrossModel | moonshot/kimi-k3 | 1,048,576 | 1,048,576 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Deep Infra | moonshotai/Kimi-K3 | 1,048,576 | 131,072 | $2.85 / $14.25 | Yes | Yes | Yes | View |
| DevPass (LLM Gateway) | kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| DevPass (LLM Gateway) | kimi-k3-fast | 1,040,384 | 131,072 | $4.50 / $22.50 | Yes | Yes | Yes | View |
| DigitalOcean | kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Eden AI | moonshot/kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| EmpirioLabs AI | kimi-k3 | 1,000,000 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| engy | kimi-k3 | 1,113,088 | 65,536 | $1.95 / $9.75 | Yes | Yes | Yes | View |
| Fireworks AI | accounts/fireworks/models/kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Fireworks AI | accounts/fireworks/routers/kimi-k3-fast | 1,048,576 | 131,072 | $4.50 / $22.50 | Yes | Yes | Yes | View |
| Fireworks AI | accounts/fireworks/routers/kimi-latest | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Fireworks AI | accounts/fireworks/routers/kimi-fast-latest | 1,048,576 | 131,072 | $4.50 / $22.50 | Yes | Yes | Yes | View |
| GitHub Copilot | kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| GreenPT | kimi-k3 | 1,048,576 | 131,072 | $3.762 / $18.81 | Yes | Yes | Yes | View |
| Hugging Face | moonshotai/Kimi-K3 | 1,000,000 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Impossibl | moonshotai/kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Inco | kimi-k3:fast | 1,048,576 | 131,072 | $6.00 / $30.00 | Yes | Yes | Yes | View |
| IteraCompute | moonshotai/kimi-k3 | 1,048,576 | 999,999 | $3.00 / $14.90 | Yes | Yes | No | View |
| Jalapeno Cloud | Kimi-K3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Kenari | kimi-k3 | 1,048,576 | 131,072 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| Kilo Gateway | moonshotai/kimi-k3 | 1,048,576 | 943,718 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Kimi For Coding (kimi.ai) | k3-256k | 262,144 | 131,072 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| Kimi For Coding (kimi.ai) | k3 | 1,048,576 | 131,072 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| Kimi For Coding (kimi.com) | k3-256k | 262,144 | 131,072 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| Kimi For Coding (kimi.com) | k3 | 1,048,576 | 131,072 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| LLM Gateway | aws-bedrock/kimi-k3 | 1,048,576 | 1,048,576 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| LLM Gateway | together-ai/kimi-k3 | 1,000,000 | 1,000,000 | $3.00 / $15.00 | Yes | Yes | No | View |
| LLM Gateway | novita/kimi-k3 | 1,048,576 | 1,048,576 | $3.00 / $15.00 | Yes | Yes | No | View |
| LLM Gateway | scx-ai-gp/kimi-k3 | 1,048,576 | 1,048,576 | $3.50 / $18.00 | Yes | Yes | Yes | View |
| LLM Gateway | tencent/kimi-k3 | 1,048,576 | 1,048,576 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| LLM Gateway | fireworks/kimi-k3 | 1,040,384 | 1,040,384 | $3.00 / $15.00 | Yes | Yes | No | View |
| LLM Gateway | canopywave/kimi-k3 | 1,048,576 | 1,048,576 | $3.00 / $15.00 | Yes | Yes | No | View |
| LLM Gateway | runpod/kimi-k3 | 1,048,576 | 1,048,576 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| LLM Gateway | runware/kimi-k3 | 1,048,576 | 1,048,576 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| LLM Gateway | moonshot/kimi-k3 | 1,048,576 | 1,048,576 | $3.00 / $15.00 | Yes | Yes | No | View |
| LLM Gateway | alibaba/kimi-k3 | 1,048,576 | 1,048,576 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| LLM Gateway | fireworks/kimi-k3-fast | 1,040,384 | 1,040,384 | $4.50 / $22.50 | Yes | Yes | No | View |
| Melious | kimi-k3 | 1,000,000 | 131,072 | $3.1878 / $15.939 | Yes | Yes | Yes | View |
| Merge Gateway | moonshot/kimi-k3 | 1,048,576 | 1,048,576 | $2.90 / $14.00 | Yes | Yes | Yes | View |
| Modal | moonshotai/Kimi-K3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Moonshot AI | kimi-k3 | 1,048,576 | 1,048,576 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Moonshot AI (China) | kimi-k3 | 1,048,576 | 1,048,576 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| NanoGPT | TEE/kimi-k3 | 1,048,576 | 65,535 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| NanoGPT | moonshotai/kimi-k3 | 1,048,576 | 943,718 | $2.00 / $10.00 | Yes | Yes | Yes | View |
| Nebius Token Factory | moonshotai/Kimi-K3 | 1,048,576 | 8,000 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Neon | kimi-k3 | 1,048,576 | 65,536 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Neuralwatt | kimi-k3-flex | 1,048,560 | 1,048,560 | $1.95 / $9.75 | Yes | Yes | Yes | View |
| Neuralwatt | kimi-k3 | 1,048,560 | 1,048,560 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Neuralwatt | kimi-k3-fast | 1,048,560 | 1,048,560 | $3.00 / $15.00 | No | Yes | Yes | View |
| NovitaAI | moonshotai/kimi-k3 | 1,048,576 | 1,048,576 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Nvidia | moonshotai/kimi-k3 | 1,048,576 | 131,072 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| Ofox | moonshotai/kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Ollama Cloud | kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| OpenCode Go | kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| OpenCode Zen | kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| AkashMLvia OpenRouter | moonshotai/kimi-k3 fp4 | 1,048,576 | 943,718 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Alibabavia OpenRouter | moonshotai/kimi-k3 unknown | 1,048,576 | 131,072 | $3.45 / $17.25 | Yes | Yes | Yes | View |
| Amazon Bedrockvia OpenRouter | moonshotai/kimi-k3 unknown | 1,048,576 | 128,000 | $3.00 / $15.00 | Yes | Yes | No | View |
| BaseTenvia OpenRouter | moonshotai/kimi-k3 fp8 | 1,048,576 | 262,144 | $3.00 / $15.00 | Yes | Yes | No | View |
| Chutesvia OpenRouter | moonshotai/kimi-k3 mxfp4 | 1,048,576 | 65,535 | $3.00 / $15.00 | Yes | No | Yes | View |
| Decartvia OpenRouter | moonshotai/kimi-k3 mxfp4 | 1,048,576 | 943,718 | $2.25 / $11.25 | Yes | Yes | Yes | View |
| DeepInfravia OpenRouter | moonshotai/kimi-k3 mxfp4 | 1,048,576 | 943,718 | $2.85 / $14.25 | Yes | Yes | Yes | View |
| DigitalOceanvia OpenRouter | moonshotai/kimi-k3 unknown | 1,048,576 | 943,718 | $2.55 / $12.95 | Yes | Yes | No | View |
| Fireworksvia OpenRouter | moonshotai/kimi-k3 unknown | 1,048,576 | 943,718 | $4.50 / $22.50 | Yes | Yes | Yes | View |
| Fireworksvia OpenRouter | moonshotai/kimi-k3 unknown | 1,048,576 | 943,718 | $4.50 / $22.50 | Yes | No | Yes | View |
| Fireworksvia OpenRouter | moonshotai/kimi-k3 unknown | 1,048,576 | 943,718 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| InferenceNetvia OpenRouter | moonshotai/kimi-k3 fp4 | 250,000 | 225,000 | $3.50 / $20.00 | Yes | Yes | Yes | View |
| InferenceNetvia OpenRouter | moonshotai/kimi-k3 fp4 | 1,048,576 | 943,718 | $0.72 / $13.00 | Yes | Yes | Yes | View |
| Makoravia OpenRouter | moonshotai/kimi-k3 unknown | 1,048,576 | 943,718 | $2.04 / $12.75 | Yes | Yes | Yes | View |
| Modalvia OpenRouter | moonshotai/kimi-k3 mxfp4 | 1,048,576 | 943,718 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Moonshot AIvia OpenRouter | moonshotai/kimi-k3 mxfp4 | 1,048,576 | 943,718 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Morphvia OpenRouter | moonshotai/kimi-k3 fp8 | 1,048,576 | 943,718 | $1.25 / $11.822 | Yes | Yes | Yes | View |
| Parasailvia OpenRouter | moonshotai/kimi-k3 fp4 | 1,048,576 | 943,718 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Phalavia OpenRouter | moonshotai/kimi-k3 unknown | 1,048,576 | 943,718 | $2.25 / $11.25 | Yes | Yes | Yes | View |
| Relacevia OpenRouter | moonshotai/kimi-k3 fp4 | 1,048,576 | 943,718 | $0.6438 / $13.00 | Yes | Yes | No | View |
| Sail Researchvia OpenRouter | moonshotai/kimi-k3 fp4 | 1,048,576 | 943,718 | $2.80 / $14.00 | Yes | Yes | Yes | View |
| Togethervia OpenRouter | moonshotai/kimi-k3 unknown | 1,048,576 | 943,718 | $2.70 / $13.50 | Yes | Yes | Yes | View |
| Wafervia OpenRouter | moonshotai/kimi-k3 unknown | 1,048,576 | 943,718 | $0.73 / $13.00 | Yes | Yes | Yes | View |
| Wafervia OpenRouter | moonshotai/kimi-k3 unknown | 1,048,576 | 943,718 | $2.80 / $14.00 | Yes | Yes | Yes | View |
| Opper | kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| OrcaRouter | kimi/kimi-k3 | 1,048,576 | 131,072 | $3.30 / $16.50 | Yes | Yes | Yes | View |
| Perplexity Agent | moonshot-ai/kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Pioneer | moonshotai/Kimi-K3 | 1,000,000 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Pioneer | moonshotai/Kimi-K3-Fast | 1,000,000 | 131,072 | $4.50 / $22.50 | Yes | Yes | Yes | View |
| Requesty | kimi-k3@eu | 1,048,576 | 262,144 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Requesty | kimi-k3 | 1,048,576 | 262,144 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| SCNet Token Plan | Kimi-K3 | 1,048,576 | 131,072 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| SenseNova (China) | kimi-k3 | 1,048,576 | 65,536 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| SiliconFlow | moonshotai/Kimi-K3 | 1,048,576 | 262,000 | $2.70 / $13.50 | Yes | Yes | Yes | View |
| Synthetic | hf:moonshotai/Kimi-K3 | 524,288 | 65,536 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Tempr Gateway | moonshot/kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| TensorX | moonshotai/kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Tinfoil | kimi-k3 | 262,144 | 131,072 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Together AI | moonshotai/Kimi-K3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| TokenGo | moonshotai/kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Umans AI | umans-kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Umans AI Coding Plan | umans-kimi-k3 | 1,048,576 | 131,072 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| Vancine | kimi-k3 | 1,048,576 | 131,072 | $2.40 / $12.00 | Yes | Yes | Yes | View |
| Venice AI | kimi-k3 | 1,000,000 | 131,072 | $3.75 / $18.75 | Yes | Yes | Yes | View |
| Venice AI | kimi-k3-fast-api | 1,000,000 | 131,072 | $4.50 / $22.50 | Yes | Yes | Yes | View |
| Vercel AI Gateway | moonshotai/kimi-k3 | 1,000,000 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Vercel AI Gateway | moonshotai/kimi-k3-fast | 1,000,000 | 131,072 | $4.50 / $22.50 | Yes | Yes | Yes | View |
| Vivgrid | kimi-k3 | 1,000,000 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| Volcengine Ark Coding Plan | kimi-k3 | 1,048,576 | 131,072 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| Wallaby | moonshotai/kimi-k3 | 1,048,576 | 131,072 | $2.70 / $13.50 | Yes | Yes | Yes | View |
| ZenMux | moonshotai/kimi-k3 | 1,048,576 | 131,072 | $3.00 / $15.00 | Yes | Yes | Yes | View |
| ZenMux | moonshotai/kimi-k3-free | 1,048,576 | 131,072 | $0.00 / $0.00 | Yes | Yes | Yes | View |
Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.
Pricing
Compare token rates and cache charges across available routes and hosting configurations.
Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.
moonshotai/kimi-k3Observed - Input
- $0.72
- Output
- $13.00
- Cache read
- $0.70
Hosting prices through OpenRouter All endpoints and cache rates
| Endpoint | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
| AkashMLakashml/fp4 | $3.00 | $15.00 | $0.30 | — |
| Alibabaalibaba | $3.45 | $17.25 | $0.345 | — |
| Amazon Bedrockamazon-bedrock/us-east-2 | $3.00 | $15.00 | $0.30 | $3.75 |
| BaseTenbaseten/fp8 | $3.00 | $15.00 | $0.30 | — |
| Chuteschutes/mxfp4 | $3.00 | $15.00 | $0.30 | — |
| Decartdecart/mxfp4 | $2.25 | $11.25 | $0.225 | — |
| DeepInfradeepinfra/mxfp4 | $2.85 | $14.25 | $0.285 | — |
| DigitalOceandigitalocean | $2.55 | $12.95 | $0.255 | — |
| Fireworksfireworks/us | $4.50 | $22.50 | $0.45 | — |
| Fireworksfireworks/fast | $4.50 | $22.50 | $0.45 | — |
| Fireworksfireworks | $3.00 | $15.00 | $0.30 | — |
| InferenceNetinference-net/fast | $3.50 | $20.00 | $0.45 | — |
| InferenceNetinference-net/fp4 | $0.72 | $13.00 | $0.70 | — |
| Makoramakora | $2.04 | $12.75 | $0.204 | — |
| Modalmodal/mxfp4 | $3.00 | $15.00 | $0.30 | — |
| Moonshot AImoonshotai/mxfp4 | $3.00 | $15.00 | $0.30 | — |
| Morphmorph/fp8 | $1.25 | $11.822 | $0.29 | — |
| Parasailparasail/fp4 | $3.00 | $15.00 | $0.30 | — |
| Phalaphala | $2.25 | $11.25 | $0.225 | — |
| Relacerelace/fp4 | $0.6438 | $13.00 | $0.45 | — |
| Sail Researchsail-research/fp4 | $2.80 | $14.00 | $0.30 | — |
| Togethertogether | $2.70 | $13.50 | $0.27 | — |
| Waferwafer | $0.73 | $13.00 | $0.30 | — |
| Waferwafer/us | $2.80 | $14.00 | $0.30 | — |
Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.
Performance
Review reported latency and output-throughput percentiles from the latest observed rolling window.
Time to first token · milliseconds
All latency percentiles 21 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| AkashMLakashml/fp4 | 1,102 ms | 1,661.5 ms | 2,535 ms | 3,553.3 ms |
| Alibabaalibaba | 1,949.5 ms | 2,575 ms | 3,401.7 ms | 6,994.56 ms |
| Amazon Bedrockamazon-bedrock/us-east-2 | 1,686.5 ms | 2,452.25 ms | 4,073.1 ms | 11,688.82 ms |
| BaseTenbaseten/fp8 | 1,836.5 ms | 2,831.5 ms | 4,161 ms | 12,626.2 ms |
| Chuteschutes/mxfp4 | 1,693 ms | 2,416.5 ms | 4,337.8 ms | 17,361.82 ms |
| Decartdecart/mxfp4 | 554.5 ms | 723.75 ms | 951.5 ms | 5,871.1 ms |
| DeepInfradeepinfra/mxfp4 | 1,144 ms | 1,717.5 ms | 2,365.6 ms | 4,332.26 ms |
| DigitalOceandigitalocean | 1,013 ms | 1,548 ms | 2,242 ms | 3,282.2 ms |
| Fireworksfireworks/us | 3,006 ms | 5,026 ms | 6,621.2 ms | 12,270.76 ms |
| Fireworksfireworks/fast | 873.5 ms | 1,141.5 ms | 1,559.5 ms | 4,833.75 ms |
| Fireworksfireworks | 1,559 ms | 2,547 ms | 3,555.7 ms | 5,037.99 ms |
| InferenceNetinference-net/fast | 606 ms | 906 ms | 1,343 ms | 3,587.4 ms |
| InferenceNetinference-net/fp4 | 1,035 ms | 1,578 ms | 2,707.6 ms | 8,925.21 ms |
| Makoramakora | 1,400.5 ms | 2,758.5 ms | 5,050 ms | 16,225.05 ms |
| Modalmodal/mxfp4 | 888 ms | 1,572 ms | 2,420.8 ms | 14,370.08 ms |
| Moonshot AImoonshotai/mxfp4 | 4,354 ms | 6,116.5 ms | 9,669 ms | 27,036.88 ms |
| Parasailparasail/fp4 | 1,675 ms | 3,272 ms | 5,814.4 ms | 27,418.11 ms |
| Phalaphala | 1,678 ms | 3,378 ms | 6,335.4 ms | 28,633.46 ms |
| Togethertogether | 1,276 ms | 2,179.25 ms | 3,331 ms | 8,686.52 ms |
| Waferwafer | 873.5 ms | 1,749.75 ms | 4,247.5 ms | 19,800.7 ms |
| Waferwafer/us | 913 ms | 1,440.25 ms | 5,450.5 ms | 35,006.75 ms |
Output throughput · tokens per second
All throughput percentiles 21 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| AkashMLakashml/fp4 | 65 t/s | 73.5 t/s | 91.4 t/s | 98.14 t/s |
| Alibabaalibaba | 49 t/s | 56 t/s | 62 t/s | 74 t/s |
| Amazon Bedrockamazon-bedrock/us-east-2 | 97 t/s | 130 t/s | 157 t/s | 200.7 t/s |
| BaseTenbaseten/fp8 | 67 t/s | 82 t/s | 111 t/s | 155.9 t/s |
| Chuteschutes/mxfp4 | 20 t/s | 23 t/s | 26 t/s | 31.16 t/s |
| Decartdecart/mxfp4 | 87 t/s | 103 t/s | 122 t/s | 179.5 t/s |
| DeepInfradeepinfra/mxfp4 | 32 t/s | 41 t/s | 49 t/s | 65 t/s |
| DigitalOceandigitalocean | 36 t/s | 39 t/s | 41.8 t/s | 45 t/s |
| Fireworksfireworks/us | 46 t/s | 60 t/s | 72 t/s | 94.82 t/s |
| Fireworksfireworks/fast | 66 t/s | 92 t/s | 139.8 t/s | 184.96 t/s |
| Fireworksfireworks | 34 t/s | 41 t/s | 47 t/s | 57 t/s |
| InferenceNetinference-net/fast | 74 t/s | 98 t/s | 123 t/s | 193 t/s |
| InferenceNetinference-net/fp4 | 41 t/s | 52 t/s | 65 t/s | 89 t/s |
| Makoramakora | 51 t/s | 62 t/s | 71 t/s | 82 t/s |
| Modalmodal/mxfp4 | 60 t/s | 76 t/s | 96 t/s | 136 t/s |
| Moonshot AImoonshotai/mxfp4 | 29 t/s | 35 t/s | 40 t/s | 50 t/s |
| Parasailparasail/fp4 | 65 t/s | 91 t/s | 119 t/s | 177 t/s |
| Phalaphala | 50 t/s | 88 t/s | 119 t/s | 204.26 t/s |
| Togethertogether | 57 t/s | 76 t/s | 98 t/s | 147 t/s |
| Waferwafer | 41 t/s | 51 t/s | 62 t/s | 87 t/s |
| Waferwafer/us | 41 t/s | 54.5 t/s | 58.2 t/s | 78.88 t/s |
Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.
Uptime
Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.
Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.
Benchmarks
Review attributed evaluation results on each source's original scale.
moonshotai/kimi-k3Observed | Design Arena | Category | Elo | Win rate | Rank |
|---|---|---|---|---|
| agents | agenticgamedev | 1,252 | 55% | 3 |
| agents | androidnative | 1,262 | 55.4% | 5 |
| agents | fullstack | 1,313 | 61.8% | 2 |
| agents | godotgamedev | 1,223 | 48.2% | 14 |
| agents | htmlslides | 1,256 | 59.6% | 2 |
| agents | mobileapps | 1,266 | 56.9% | 3 |
| agents | python-pptxslides | 1,273 | 59.2% | 4 |
| agents | webapps | 1,285 | 59.1% | 4 |
| models | 3d | 1,407 | 68% | 4 |
| models | codecategories | 1,372 | 63.4% | 2 |
| models | dataviz | 1,358 | 64% | 3 |
| models | gamedev | 1,379 | 61.8% | 3 |
| models | svg | 1,299 | 59.4% | 6 |
| models | uicomponent | 1,362 | 62.3% | 3 |
| models | website | 1,344 | 59.9% | 2 |
Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.
Detailed evaluations
| Evaluation | Configuration | Source | Results | Details |
|---|---|---|---|---|
| tau bench verified airline | MoonshotAI: Kimi K3moonshotai/kimi-k3-20260715 | OpenRouter | 71.917% | Details |
| models · website | Kimi K3moonshotai/kimi-k3-20260715 | Design Arena | 1,344 Elo | Details |
| models · codecategories | Kimi K3moonshotai/kimi-k3-20260715 | Design Arena | 1,372 Elo | Details |
| gpqa diamond | MoonshotAI: Kimi K3moonshotai/kimi-k3-20260715 | OpenRouter | 91.854% | Details |
| models · uicomponent | Kimi K3moonshotai/kimi-k3-20260715 | Design Arena | 1,362 Elo | Details |
| Composite indices | Kimi K3 (Max)moonshotai/kimi-k3-20260715 | Artificial Analysis | Intelligence 43.6 · Coding 76.2 · Agentic 50 | Details |
| models · 3d | Kimi K3moonshotai/kimi-k3-20260715 | Design Arena | 1,407 Elo | Details |
| models · dataviz | Kimi K3moonshotai/kimi-k3-20260715 | Design Arena | 1,358 Elo | Details |
| models · gamedev | Kimi K3moonshotai/kimi-k3-20260715 | Design Arena | 1,379 Elo | Details |
| models · svg | Kimi K3moonshotai/kimi-k3-20260715 | Design Arena | 1,299 Elo | Details |
Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.
Apps & session costs
Compare observed median session costs for applications using this model, grouped by conversation length.
| Application | Model route | Turns | Median cost / session | Details |
|---|---|---|---|---|
| Claude Code | moonshotai/kimi-k3-20260715 | 1 turn | $0.061641 | Details |
| Hermes Agent | moonshotai/kimi-k3-20260715 | 50+ turns | $3.538092 | Details |
| Kilo Code | moonshotai/kimi-k3-20260715 | 10–49 turns | $0.852894 | Details |
| Claude Code | moonshotai/kimi-k3-20260715 | 50+ turns | $5.661881 | Details |
| Codex | moonshotai/kimi-k3-20260715 | 1 turn | $0.014547 | Details |
| Kilo Code | moonshotai/kimi-k3-20260715 | 2–9 turns | $0.224268 | Details |
| Codex | moonshotai/kimi-k3-20260715 | 10–49 turns | $0.602778 | Details |
| Hermes Agent | moonshotai/kimi-k3-20260715 | 2–9 turns | $0.099599 | Details |
| Hermes Agent | moonshotai/kimi-k3-20260715 | 1 turn | $0.031836 | Details |
| Claude Code | moonshotai/kimi-k3-20260715 | 2–9 turns | $0.149549 | Details |
| Codex | moonshotai/kimi-k3-20260715 | 2–9 turns | $0.106788 | Details |
| Kilo Code | moonshotai/kimi-k3-20260715 | 1 turn | $0.057958 | Details |
| Hermes Agent | moonshotai/kimi-k3-20260715 | 10–49 turns | $0.62061 | Details |
| Claude Code | moonshotai/kimi-k3-20260715 | 10–49 turns | $0.917687 | Details |
| Kilo Code | moonshotai/kimi-k3-20260715 | 50+ turns | $4.828857 | Details |
Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.
Activity
Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.
72,024,635,791 tokens
141,608,127,697 tokens
163,013,201,607 tokens
161,539,288,948 tokens
190,411,920,508 tokens
184,927,504,679 tokens
186,456,684,969 tokens
185,553,831,433 tokens
157,644,924,081 tokens
164,779,296,882 tokens
184,594,169,734 tokens
219,310,827,929 tokens
241,853,719,170 tokens
191,158,721,459 tokens
217,494,749,833 tokens
194,010,709,319 tokens
175,413,168,947 tokens
151,465,387,293 tokens
206,031,713,983 tokens
219,552,377,413 tokens
227,444,677,362 tokens
194,977,360,210 tokens
162,698,945,497 tokens
187,686,655,988 tokens
221,841,516,768 tokens
231,576,201,367 tokens
210,709,205,648 tokens
240,856,560,141 tokens
218,586,584,410 tokens
143,548,790,060 tokens
141,264,448,246 tokens
183,651,256,582 tokens
177,612,676,416 tokens
205,104,101,779 tokens
210,125,954,459 tokens
213,772,516,280 tokens
172,118,663,922 tokens
159,871,280,445 tokens
225,409,049,776 tokens
236,868,165,710 tokens
237,565,016,933 tokens
247,725,381,861 tokens
225,998,184,201 tokens
170,222,788,817 tokens
230,510,697,288 tokens
240,776,882,141 tokens
304,647,563,810 tokens
295,747,954,459 tokens
341,422,677,144 tokens
321,216,396,862 tokens
296,311,315,639 tokens
179,719,297,597 tokens
223,578,066,849 tokens
258,659,434,488 tokens
254,307,352,004 tokens
197,083,498,590 tokens
203,231,210,868 tokens
167,450,711,446 tokens
167,235,049,261 tokens
203,962,504,573 tokens
204,411,193,019 tokens
226,330,895,059 tokens
222,257,940,094 tokens
230,212,969,990 tokens
192,220,446,293 tokens
173,315,800,865 tokens
217,507,005,740 tokens
192,626,651,557 tokens
188,682,741,083 tokens
195,628,585,826 tokens
211,331,435,630 tokens
185,196,307,594 tokens
203,339,351,480 tokens
228,542,070,956 tokens
275,669,934,181 tokens
263,544,817,299 tokens
203,902,650,973 tokens
211,604,184,550 tokens
210,928,154,287 tokens
Daily observations · 79 days
| Date (UTC) | Reported tokens | Reported routes |
|---|---|---|
| Oct 3, 2026 | 210,928,154,287 | 1 |
| Oct 2, 2026 | 211,604,184,550 | 1 |
| Oct 1, 2026 | 203,902,650,973 | 1 |
| Sep 30, 2026 | 263,544,817,299 | 1 |
| Sep 29, 2026 | 275,669,934,181 | 1 |
| Sep 28, 2026 | 228,542,070,956 | 1 |
| Sep 27, 2026 | 203,339,351,480 | 1 |
| Sep 26, 2026 | 185,196,307,594 | 1 |
| Sep 25, 2026 | 211,331,435,630 | 1 |
| Sep 24, 2026 | 195,628,585,826 | 1 |
| Sep 23, 2026 | 188,682,741,083 | 1 |
| Sep 22, 2026 | 192,626,651,557 | 1 |
| Sep 21, 2026 | 217,507,005,740 | 1 |
| Sep 20, 2026 | 173,315,800,865 | 1 |
| Sep 19, 2026 | 192,220,446,293 | 1 |
| Sep 18, 2026 | 230,212,969,990 | 1 |
| Sep 17, 2026 | 222,257,940,094 | 1 |
| Sep 16, 2026 | 226,330,895,059 | 1 |
| Sep 15, 2026 | 204,411,193,019 | 1 |
| Sep 14, 2026 | 203,962,504,573 | 1 |
| Sep 13, 2026 | 167,235,049,261 | 1 |
| Sep 12, 2026 | 167,450,711,446 | 1 |
| Sep 11, 2026 | 203,231,210,868 | 1 |
| Sep 10, 2026 | 197,083,498,590 | 1 |
| Sep 9, 2026 | 254,307,352,004 | 1 |
| Sep 8, 2026 | 258,659,434,488 | 1 |
| Sep 7, 2026 | 223,578,066,849 | 1 |
| Sep 6, 2026 | 179,719,297,597 | 1 |
| Sep 5, 2026 | 296,311,315,639 | 1 |
| Sep 4, 2026 | 321,216,396,862 | 1 |
| Sep 3, 2026 | 341,422,677,144 | 1 |
| Sep 2, 2026 | 295,747,954,459 | 1 |
| Sep 1, 2026 | 304,647,563,810 | 1 |
| Aug 31, 2026 | 240,776,882,141 | 1 |
| Aug 30, 2026 | 230,510,697,288 | 1 |
| Aug 29, 2026 | 170,222,788,817 | 1 |
| Aug 28, 2026 | 225,998,184,201 | 1 |
| Aug 27, 2026 | 247,725,381,861 | 1 |
| Aug 26, 2026 | 237,565,016,933 | 1 |
| Aug 25, 2026 | 236,868,165,710 | 1 |
| Aug 24, 2026 | 225,409,049,776 | 1 |
| Aug 23, 2026 | 159,871,280,445 | 1 |
| Aug 22, 2026 | 172,118,663,922 | 1 |
| Aug 21, 2026 | 213,772,516,280 | 1 |
| Aug 20, 2026 | 210,125,954,459 | 1 |
| Aug 19, 2026 | 205,104,101,779 | 1 |
| Aug 18, 2026 | 177,612,676,416 | 1 |
| Aug 17, 2026 | 183,651,256,582 | 1 |
| Aug 16, 2026 | 141,264,448,246 | 1 |
| Aug 15, 2026 | 143,548,790,060 | 1 |
| Aug 14, 2026 | 218,586,584,410 | 1 |
| Aug 13, 2026 | 240,856,560,141 | 1 |
| Aug 12, 2026 | 210,709,205,648 | 1 |
| Aug 11, 2026 | 231,576,201,367 | 1 |
| Aug 10, 2026 | 221,841,516,768 | 1 |
| Aug 9, 2026 | 187,686,655,988 | 1 |
| Aug 8, 2026 | 162,698,945,497 | 1 |
| Aug 7, 2026 | 194,977,360,210 | 1 |
| Aug 6, 2026 | 227,444,677,362 | 1 |
| Aug 5, 2026 | 219,552,377,413 | 1 |
| Aug 4, 2026 | 206,031,713,983 | 1 |
| Aug 3, 2026 | 151,465,387,293 | 1 |
| Aug 2, 2026 | 175,413,168,947 | 1 |
| Aug 1, 2026 | 194,010,709,319 | 1 |
| Jul 31, 2026 | 217,494,749,833 | 1 |
| Jul 30, 2026 | 191,158,721,459 | 1 |
| Jul 29, 2026 | 241,853,719,170 | 1 |
| Jul 28, 2026 | 219,310,827,929 | 1 |
| Jul 27, 2026 | 184,594,169,734 | 1 |
| Jul 26, 2026 | 164,779,296,882 | 1 |
| Jul 25, 2026 | 157,644,924,081 | 1 |
| Jul 24, 2026 | 185,553,831,433 | 1 |
| Jul 23, 2026 | 186,456,684,969 | 1 |
| Jul 22, 2026 | 184,927,504,679 | 1 |
| Jul 21, 2026 | 190,411,920,508 | 1 |
| Jul 20, 2026 | 161,539,288,948 | 1 |
| Jul 19, 2026 | 163,013,201,607 | 1 |
| Jul 18, 2026 | 141,608,127,697 | 1 |
| Jul 17, 2026 | 72,024,635,791 | 1 |
Source: OpenRouter (openrouter.ai/rankings), as of Oct 4, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.
Technical details & API
Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.
moonshotai/kimi-k3Observed - Context
- 1,048,576
- Maximum output
- 943,718
- Tokenizer
- Other
- Input
- text, image, video
- Output
- text
- Moderation
- No
- Added to OpenRouter
- 2026-07-16
https://openrouter.ai/api/v1moonshotai/kimi-k3moonshotai/kimi-k3-20260715moonshotai/Kimi-K3Reasoning
- Required
- No
- Enabled by default
- Yes
- Default effort
- max
- Supported efforts
- max, high, low
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Default parameters
- top p
- 0.95
Frequently asked questions
Answers based on the model metadata and serving offers currently in the catalog.
How much does Kimi K3 cost?
Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.
Which providers offer Kimi K3?
There are 126 cataloged offers across 76 providers. Compare model IDs, prices and limits in Providers.
What is the context window?
The cataloged model context is 1,048,576 tokens. Each serving endpoint may apply a different limit.
Does it support tools and structured output?
Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.
Catalog history · 2 recorded revisions
Metadata observations since this model was first cataloged. These are not model release versions.
- ·
0a125e654385 - ·
c7865f02a448