Moonshot AI model product
Kimi K2.6
6 is Moonshot AI's open-source, native multimodal agentic model focused on state-of-the-art coding, long-horizon execution, and agent swarm capabilities.
Updated Aug 12, 2026. Default version: Kimi K2.6
LLMBoard score75.5Kimi K2.6
Coverage80%28 benchmark families
Context window262.1KTokens
Official input price$0.95Moonshot AI API
Kimi K2.6 Specifications
Technical details for the model's default version.
- Version
- Kimi K2.6
- Released
- Apr 20, 2026
- Knowledge cutoff
- Jan 1, 2025
- Parameters
- 1T
- Context window
- 262.1K
- Max output
- 262.1K
- Inputs
- image, text, video
- Outputs
- text
- Open weights
- Yes
- License
- Modified MIT License
Kimi K2.6 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Kimi K2.6 Benchmark Results
Benchmark scores for Kimi K2.6.
| Claw-Eval | 80.9% | 01 | 13 | 100.0% | C | |
| OJBench | 60.6% | 01 | 9 | 100.0% | C | |
| V* | 96.9% | 01 | 7 | 100.0% | C | |
| WideSearch | 80.8% | 01 | 9 | 100.0% | C | |
| AIME 2026 | 96.4% | 02 | 18 | 94.1% | C | |
| LiveCodeBench v6 | 89.6% | 02 | 53 | 98.1% | C | |
| MathVision | 93.2% | 03 | 32 | 93.5% | C | |
| MCP-Mark | 55.9% | 04 | 8 | 57.1% | C | |
| APEX-Agents | 27.9% | 05 | 7 | 33.3% | C | |
| BabyVision | 68.5% | 05 | 9 | 50.0% | C | |
| HMMT Feb 26 | 92.7% | 05 | 11 | 60.0% | C | |
| SciCode | 52.2% | 05 | 19 | 77.8% | C | |
| DeepSearchQA | 83.0% | 06 | 9 | 37.5% | C | |
| SWE-bench Multilingual | 76.7% | 06 | 34 | 84.8% | C | |
| BrowseComp | 86.3% | 07 | 58 | 89.5% | C | |
| IMO-AnswerBench | 86.0% | 07 | 19 | 66.7% | C | |
| CharXiv-R | 86.7% | 08 | 48 | 85.1% | C | |
| Finance Agent v2 | 44.9% | 11 | 26 | 60.0% | B | |
| SWE-Bench Verified | 80.2% | 12 | 105 | 89.4% | C | |
| FrontierSWE | 27.0% | 13 | 15 | 14.3% | B | |
| MMMU-Pro | 80.1% | 14 | 66 | 80.0% | C | |
| OSWorld-Verified | 73.1% | 14 | 23 | 40.9% | C | |
| Toolathlon | 50.0% | 14 | 31 | 56.7% | C | |
| Terminal-Bench 2.0 | 66.7% | 15 | 49 | 70.8% | C | |
| SWE-Bench Pro | 58.6% | 17 | 45 | 63.6% | C | |
| GPQA | 90.5% | 19 | 234 | 92.3% | C | |
| LiveBench | 72.2% | 25 | 38 | 35.1% | B | |
| Humanity's Last Exam | 36.4% | 39 | 93 | 58.7% | C |
Kimi K2.6 Arena Results
Preference and agent-evaluation results for the default version.
| agent tool hallucination | overall | 03 | 0.0 | N/A | 288.1K | |
| agent task outcome explicit | overall | 21 | 0.0 | N/A | 5.7K | |
| document | overall | 21 | 1450.9 | 11,181 | N/A | |
| agent praise complaint | overall | 23 | 0.0 | N/A | 1.7K | |
| document style control | overall | 25 | 1449.5 | 11,181 | N/A | |
| vision | overall | 26 | 1281.4 | 15,386 | N/A | |
| agent | overall | 27 | -0.0 | N/A | 311.7K | |
| agent steerability | overall | 27 | -0.0 | N/A | 6.6K | |
| webdev | overall | 27 | 1509.2 | 9,587 | N/A | |
| vision style control | overall | 30 | 1263.4 | 15,386 | N/A | |
| text | overall | 32 | 1454.7 | 37,626 | N/A | |
| agent bash recovery steps | overall | 37 | -0.1 | N/A | 9.5K | |
| text factuality | overall | 41 | 1455.1 | 37,580 | N/A | |
| text style control | overall | 44 | 1460.4 | 37,626 | N/A |
Kimi K2.6 Runtime Performance
Provider-specific output speed and catalog latency for Kimi K2.6. Runtime does not affect the capability score.
| Moonshot AI | 87.929 tok/s | 1.641 s | 262.1K | 262.1K | |
| Novita | 66.349 tok/s | 1.67 s | 262.1K | 262.1K | |
| Fireworks | 23.792 tok/s | 0.341 s | 262.1K | 262.1K | |
| DeepInfra | 13.357 tok/s | 19.574 s | 262.1K | 131.1K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Kimi K2.6 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.95 input, $4 output per 1M
- Official provider
- Moonshot AI
- Lowest third-party
- From $0.22 input, $1.14 output per 1M via LLM Gateway
- Tracked offerings
- 63
| Nvidia | moonshotai/kimi-k2.6 | global | N/A | N/A | 262.1K | |
| Kenari | kimi-k2-6 | global | N/A | N/A | 262.1K | |
| Privatemode AI | kimi-k2.6 | global | N/A | N/A | 262.1K | |
| Alibaba Token Plan | kimi-k2.6 | global | N/A | N/A | 262.1K | |
| Alibaba Token Plan (China) | kimi-k2.6 | global | N/A | N/A | 262.1K | |
| LLM Gateway | kimi-k2.6 | global | $0.22 | $1.14 | 262.1K | |
| routing.run | kimi-k2.6 | global | $0.275 | $1.1 | 200K | |
| Vultr | moonshotai/Kimi-K2.6 | global | $0.30 | $1.2 | 262.1K | |
| NanoGPT | moonshotai/kimi-k2.6 | global | $0.50 | $2.6 | 256K | |
| CrofAI | kimi-k2.6 | global | $0.50 | $1.99 | 262.1K | |
| Weights & Biases | moonshotai/Kimi-K2.6 | global | $0.65 | $3.41 | 262.1K | |
| Inceptron | moonshotai/Kimi-K2.6 | global | $0.66 | $3.5 | 262.1K | |
| Neuralwatt | moonshotai/Kimi-K2.6 | global | $0.69 | $3.22 | 262.1K | |
| Lilac | moonshotai/kimi-k2.6 | global | $0.70 | $3.5 | 262.1K | |
| Infomaniak | moonshotai/Kimi-K2.6 | global | $0.74 | $3.72 | 256K | |
| FastRouter | moonshotai/kimi-k2.6 | global | $0.75 | $3.5 | 262.1K | |
| Venice AI | kimi-k2-6 | global | $0.75 | $3.5 | 256K | |
| Deep Infra | moonshotai/Kimi-K2.6 | global | $0.75 | $3.5 | 262.1K | |
| GreenPT | kimi-k2.6 | global | $0.7524 | $4.28 | 262.1K | |
| DigitalOcean | kimi-k2.6 | global | $0.76 | $3.2 | 262.1K | |
| SiliconFlow | moonshotai/Kimi-K2.6 | global | $0.77 | $4 | 262K | |
| Cortecs | kimi-k2.6 | global | $0.773 | $3.38 | 262.1K | |
| Kilo Gateway | moonshotai/kimi-k2.6 | global | $0.80 | $3.4 | 262.1K | |
| NovitaAI | moonshotai/kimi-k2.6 | global | $0.80 | $3.4 | 262.1K | |
| Berget.AI | moonshotai/Kimi-K2.6 | global | $0.83 | $3.85 | 262.1K | |
| GMI Cloud | moonshotai/Kimi-K2.6 | global | $0.855 | $3.6 | 65.5K | |
| EmpirioLabs AI | kimi-k2-6 | global | $0.8939 | $3.71 | 256K | |
| EBCloud | Kimi-K2.6 | global | $0.9286 | $3.86 | 262.1K | |
| Alibaba (China) | kimi-k2.6 | global | $0.929 | $3.86 | 262.1K | |
| Fireworks AI | accounts/fireworks/models/kimi-k2p6 | global | $0.95 | $4 | 262K | |
| OpenCode Go | kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| Baseten | moonshotai/Kimi-K2.6 | global | $0.95 | $4 | 262K | |
| OpenCode Zen | kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| Cloudflare Workers AI | @cf/moonshotai/kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| Ambient | moonshotai/kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| FrogBot | kimi-k2-6 | global | $0.95 | $4 | 256K | |
| ClinePass | cline-pass/kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| Pioneer | moonshotai/Kimi-K2.6 | global | $0.95 | $4 | 262.1K | |
| ZenMux | moonshotai/kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| Abacus | moonshotai/Kimi-K2.6 | global | $0.95 | $4 | 262.1K | |
| Azure Cognitive Services | kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| Clarifai | moonshotai/chat-completion/models/Kimi-K2_6 | global | $0.95 | $4 | 262.1K | |
| Moonshot AI (China) | kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| Auriko | kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| Azure | kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| AIHubMix | kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| Ofox | moonshotai/kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| OrcaRouter | kimi/kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| Merge Gateway | moonshot/kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| Charm Hyper | kimi-k2.6 | global | $0.95 | $4 | 262K | |
| Vercel AI Gateway | moonshotai/kimi-k2.6 | global | $0.95 | $4 | 262K | |
| OpenRouter | moonshotai/kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| Hugging Face | moonshotai/Kimi-K2.6 | global | $0.95 | $4 | 262.1K | |
| Cloudflare AI Gateway | workers-ai/@cf/moonshotai/kimi-k2.6 | global | $0.95 | $4 | 256K | |
| Moonshot AI | kimi-k2.6 | global | $0.95 | $4 | 262.1K | |
| Poe | novita/kimi-k2.6 | global | $0.96 | $4.04 | 262.1K | |
| CrossModel | moonshot/kimi-k2.6 | global | $1 | $4.16 | 262K | |
| TensorX | moonshotai/kimi-k2.6 | global | $1 | $4 | 262.1K | |
| Wafer | Kimi-K2.6 | global | $1.14 | $4.8 | 262.1K | |
| Together AI | moonshotai/Kimi-K2.6 | global | $1.2 | $4.5 | 262.1K | |
| UnoRouter | kimi-k2.6 | global | $1.27 | $5.34 | 262.1K | |
| evroc | moonshotai/Kimi-K2.6 | global | $1.44 | $5.75 | 262.1K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Kimi K2.6 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Kimi K2.6 | 75.5 | 1T | 262.1K | 262.1K | Yes | Modified MIT License |
What is Kimi K2.6?
Key information about Kimi K2.6 and its available data.
6 is Moonshot AI's open-source, native multimodal agentic model focused on state-of-the-art coding, long-horizon execution, and agent swarm capabilities. It scales horizontally to 300 sub-agents executing 4,000 coordinated steps, dynamically decomposing tasks into parallel, domain-specialized subtasks.
6 unifies text, image, and video input with thinking and non-thinking modes, supports a 256K context, and powers proactive 24/7 background agents that manage schedules, execute code, and orchestrate cross-platform operations without human oversight.
Data as of 2026-08-11.
Kimi K2.6 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Kimi K2.6
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MA
Kimi K2.7 Code
Moonshot AI
MA
Kimi K2.5
Moonshot AI
MA
Kimi K2 Thinking
Moonshot AI
MA
Kimi K3
Moonshot AI
MA
Kimi K2
Moonshot AI
MA
Kimi k1.5
Moonshot AI
FAQ
Common questions about Kimi K2.6.
When was Kimi K2.6 released?
Kimi K2.6's default version was released on Apr 20, 2026.
How much does Kimi K2.6 cost?
Kimi K2.6's official API price is $0.95 per million input tokens and $4 per million output tokens via Moonshot AI. The lowest tracked third-party offer starts at $0.22 input and $1.14 output via LLM Gateway.
Who created Kimi K2.6?
Kimi K2.6 was created by Moonshot AI.
What is the context window for Kimi K2.6?
The default version has a 262.1K token context window.
Is Kimi K2.6 open weight?
Yes. The default version is marked as open weight under Modified MIT License.
How many API providers offer Kimi K2.6?
63 provider offerings are linked to the default version.
What models should I compare Kimi K2.6 with?
Nearby ranked alternatives include GPT-5.4, GPT-5.6-Luna, GPT-5.5-Pro.