Moonshot AI model product
Kimi K2.6
6 is an open-source native multimodal agentic model from Moonshot AI for coding, long-horizon execution, and coordinated agent tasks.
Updated Sep 8, 2026. Default version: Kimi K2.6
LLMBoard Score73.5Kimi K2.6
Coverage40%28 benchmark families
Context window262.1KTokens
Official input price$0.95Moonshot AI API
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.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkClaw-Eval | Score80.90% | Rank01 | Participants14 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOJBench | Score60.60% | Rank01 | Participants9 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkV* | Score96.90% | Rank01 | Participants7 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkAIME 2026 | Score96.40% | Rank03 | Participants22 | Percentile90.48% | EvidenceC | Evaluated |
| BenchmarkWideSearch | Score80.80% | Rank03 | Participants11 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkMCP-Mark | Score55.90% | Rank04 | Participants8 | Percentile57.14% | EvidenceC | Evaluated |
| BenchmarkHMMT Feb 26 | Score92.70% | Rank05 | Participants12 | Percentile63.64% | EvidenceC | Evaluated |
| BenchmarkSciCode | Score52.20% | Rank05 | Participants24 | Percentile82.61% | EvidenceC | Evaluated |
| BenchmarkBabyVision | Score68.50% | Rank06 | Participants11 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench v6 | Score89.60% | Rank06 | Participants62 | Percentile91.80% | EvidenceC | Evaluated |
| BenchmarkMathVision | Score93.20% | Rank06 | Participants35 | Percentile85.29% | EvidenceC | Evaluated |
| BenchmarkAPEX-Agents | Score27.90% | Rank07 | Participants9 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkDeepSearchQA | Score83.00% | Rank07 | Participants10 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkIMO-AnswerBench | Score86.00% | Rank07 | Participants20 | Percentile68.42% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score86.30% | Rank08 | Participants63 | Percentile88.71% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Steerability | Score7.73% | Rank08 | Participants49 | Percentile85.42% | EvidenceA | Evaluated |
| BenchmarkSWE-bench Multilingual | Score76.70% | Rank10 | Participants43 | Percentile78.57% | EvidenceC | Evaluated |
| BenchmarkFinance Agent v2 | Score44.87% | Rank11 | Participants26 | Percentile60.00% | EvidenceB | Evaluated |
| BenchmarkLM Arena Agent Tool Hallucination | Score0.78% | Rank11 | Participants49 | Percentile79.17% | EvidenceA | Evaluated |
| BenchmarkCharXiv-R | Score86.70% | Rank13 | Participants55 | Percentile77.78% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score80.20% | Rank13 | Participants113 | Percentile89.29% | EvidenceC | Evaluated |
| BenchmarkFrontierSWE | Score27.00% | Rank14 | Participants16 | Percentile13.33% | EvidenceB | Evaluated |
| BenchmarkMMMU-Pro | Score80.10% | Rank14 | Participants69 | Percentile80.88% | EvidenceC | Evaluated |
| BenchmarkOSWorld-Verified | Score73.10% | Rank15 | Participants24 | Percentile39.13% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score66.70% | Rank15 | Participants51 | Percentile72.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Document | Score1,450.90 rating | Rank17 | Participants33 | Percentile50.00% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Praise Complaint | Score5.02% | Rank19 | Participants49 | Percentile62.50% | EvidenceA | Evaluated |
| BenchmarkLM Arena Document Style Control | Score1,449.51 rating | Rank21 | Participants33 | Percentile37.50% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,280.71 rating | Rank21 | Participants107 | Percentile81.13% | EvidenceA | Evaluated |
| BenchmarkSWE-Bench Pro | Score58.60% | Rank22 | Participants55 | Percentile61.11% | EvidenceC | Evaluated |
Kimi K2.6 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenaagent steerability | Categoryoverall | Rank08 | Rating / score0.08 | VotesN/A | Observations5.8K | Result date |
| Arenaagent tool hallucination | Categoryoverall | Rank11 | Rating / score0.01 | VotesN/A | Observations304.3K | Result date |
| Arenatext factuality | Categoryjapanese | Rank11 | Rating / score1,441.75 | Votes355 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank12 | Rating / score1,528.70 | Votes1,893 | ObservationsN/A | Result date |
| Arenatext factuality | Categorychinese | Rank13 | Rating / score1,522.11 | Votes1,655 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank14 | Rating / score1,347.86 | Votes872 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank14 | Rating / score1,328.41 | Votes872 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank16 | Rating / score1,475.11 | Votes1,737 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank16 | Rating / score1,472.85 | Votes1,682 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank16 | Rating / score1,526.03 | Votes1,893 | ObservationsN/A | Result date |
| Arenawebdev | Categoryimage to webdev | Rank16 | Rating / score1,520.95 | Votes3,356 | ObservationsN/A | Result date |
| Arenadocument | Categoryoverall | Rank17 | Rating / score1,450.90 | Votes11,181 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank18 | Rating / score1,488.05 | Votes1,222 | ObservationsN/A | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank19 | Rating / score0.05 | VotesN/A | Observations1.8K | Result date |
| Arenatext factuality | Categoryspanish | Rank19 | Rating / score1,454.54 | Votes1,080 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank19 | Rating / score1,310.13 | Votes2,147 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank19 | Rating / score1,302.22 | Votes2,147 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank20 | Rating / score1,443.45 | Votes468 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank20 | Rating / score1,427.11 | Votes714 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank20 | Rating / score1,499.49 | Votes2,940 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank20 | Rating / score1,285.87 | Votes6,404 | ObservationsN/A | Result date |
| Arenadocument style control | Categoryoverall | Rank21 | Rating / score1,449.51 | Votes11,181 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank21 | Rating / score1,478.40 | Votes1,936 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank21 | Rating / score1,290.49 | Votes11,037 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank21 | Rating / score1,280.71 | Votes15,378 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank22 | Rating / score1,298.19 | Votes4,034 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank22 | Rating / score1,277.62 | Votes539 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank23 | Rating / score1,473.25 | Votes1,936 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank23 | Rating / score1,462.62 | Votes1,321 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank23 | Rating / score1,266.61 | Votes844 | ObservationsN/A | Result date |
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 DevPass (LLM Gateway)
- Tracked offerings
- 65
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNvidia | Provider model IDmoonshotai/kimi-k2.6 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context262.1K | Updated |
| ProviderAlibaba Token Plan | Provider model IDkimi-k2.6 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context262.1K | Updated |
| ProviderKenari | Provider model IDkimi-k2-6 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context262.1K | Updated |
| ProviderSCNet Token Plan | Provider model IDKimi-K2.6 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context262.1K | Updated |
| ProviderAlibaba Token Plan (China) | Provider model IDkimi-k2.6 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context262.1K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDkimi-k2.6 | Regionglobal | Input / 1M$0.22 | Output / 1M$1.14 | Context262.1K | Updated |
| Providerrouting.run | Provider model IDkimi-k2.6 | Regionglobal | Input / 1M$0.275 | Output / 1M$1.1 | Context200K | Updated |
| ProviderVultr | Provider model IDmoonshotai/Kimi-K2.6 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context262.1K | Updated |
| ProviderNanoGPT | Provider model IDmoonshotai/kimi-k2.6 | Regionglobal | Input / 1M$0.50 | Output / 1M$2.6 | Context256K | Updated |
| ProviderCrofAI | Provider model IDkimi-k2.6 | Regionglobal | Input / 1M$0.50 | Output / 1M$1.99 | Context262.1K | Updated |
| ProviderInceptron | Provider model IDmoonshotai/Kimi-K2.6 | Regionglobal | Input / 1M$0.53 | Output / 1M$3.39 | Context262.1K | Updated |
| ProviderWeights & Biases | Provider model IDmoonshotai/Kimi-K2.6 | Regionglobal | Input / 1M$0.65 | Output / 1M$3.41 | Context262.1K | Updated |
| ProviderCrusoe | Provider model IDmoonshotai/Kimi-K2.6 | Regionglobal | Input / 1M$0.70 | Output / 1M$3.5 | Context262.1K | Updated |
| ProviderLilac | Provider model IDmoonshotai/kimi-k2.6 | Regionglobal | Input / 1M$0.70 | Output / 1M$3.5 | Context262.1K | Updated |
| ProviderInfomaniak | Provider model IDmoonshotai/Kimi-K2.6 | Regionglobal | Input / 1M$0.74 | Output / 1M$3.72 | Context256K | Updated |
| ProviderDeep Infra | Provider model IDmoonshotai/Kimi-K2.6 | Regionglobal | Input / 1M$0.75 | Output / 1M$3.5 | Context262.1K | Updated |
| ProviderFastRouter | Provider model IDmoonshotai/kimi-k2.6 | Regionglobal | Input / 1M$0.75 | Output / 1M$3.5 | Context262.1K | Updated |
| ProviderVenice AI | Provider model IDkimi-k2-6 | Regionglobal | Input / 1M$0.75 | Output / 1M$3.5 | Context256K | Updated |
| ProviderGreenPT | Provider model IDkimi-k2.6 | Regionglobal | Input / 1M$0.7524 | Output / 1M$4.28 | Context262.1K | Updated |
| ProviderSiliconFlow | Provider model IDmoonshotai/Kimi-K2.6 | Regionglobal | Input / 1M$0.77 | Output / 1M$4 | Context262K | Updated |
| ProviderCortecs | Provider model IDkimi-k2.6 | Regionglobal | Input / 1M$0.773 | Output / 1M$3.38 | Context262.1K | Updated |
| ProviderNovitaAI | Provider model IDmoonshotai/kimi-k2.6 | Regionglobal | Input / 1M$0.80 | Output / 1M$3.4 | Context262.1K | Updated |
| ProviderKilo Gateway | Provider model IDmoonshotai/kimi-k2.6 | Regionglobal | Input / 1M$0.80 | Output / 1M$3.4 | Context262.1K | Updated |
| ProviderGMI Cloud | Provider model IDmoonshotai/Kimi-K2.6 | Regionglobal | Input / 1M$0.855 | Output / 1M$3.6 | Context65.5K | Updated |
| ProviderEmpirioLabs AI | Provider model IDkimi-k2-6 | Regionglobal | Input / 1M$0.8939 | Output / 1M$3.71 | Context256K | Updated |
| ProviderEBCloud | Provider model IDKimi-K2.6 | Regionglobal | Input / 1M$0.9286 | Output / 1M$3.86 | Context262.1K | Updated |
| ProviderAlibaba (China) | Provider model IDkimi-k2.6 | Regionglobal | Input / 1M$0.929 | Output / 1M$3.86 | Context262.1K | Updated |
| ProviderCloudflare Workers AI | Provider model ID@cf/moonshotai/kimi-k2.6 | Regionglobal | Input / 1M$0.95 | Output / 1M$4 | Context262.1K | Updated |
| ProviderTokenGo | Provider model IDmoonshotai/kimi-k2.6 | Regionglobal | Input / 1M$0.95 | Output / 1M$4 | Context262.1K | Updated |
| ProviderOrcaRouter | Provider model IDkimi/kimi-k2.6 | Regionglobal | Input / 1M$0.95 | Output / 1M$4 | Context262.1K | Updated |
Kimi K2.6 Runtime Performance
Provider-specific output speed and catalog latency for Kimi K2.6. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderMoonshot AI | Output Speed1.24 tok/s | Catalog LatencyN/A | Max Input262.1K | Max Output262.1K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Kimi K2.6 Specifications
Technical details for the model's default version.
- Version
- Kimi K2.6
- Released
- Apr 20, 2026
- Knowledge cutoff
- Unknown
- 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 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionKimi K2.6 | Released | LLMBoard73.54 | Parameters1T | Context262.1K | Max output262.1K | Open weightsYes | LicenseModified MIT License |
Models similar to Kimi K2.6
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MA
Kimi K2.5
Moonshot AI
MA
Kimi K2.7 Code
Moonshot AI
MA
Kimi K2 Thinking
Moonshot AI
MA
Kimi K3
Moonshot AI
MA
Kimi K2
Moonshot AI
MA
Kimi k1.5
Moonshot AI
What is Kimi K2.6?
Key information about Kimi K2.6 and its available data.
6 is a large language model that accepts text, image, and video input and supports thinking and non-thinking modes with a 256K context. It can coordinate up to 300 sub-agents across 4,000 steps and supports background agents for scheduling, code execution, and cross-platform operations.
Data as of 2026-09-08.
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 DevPass (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?
65 provider offerings are linked to the default version.