Moonshot AI model product
Kimi K3.1 Pro
1 Pro is a multimodal model with a 1M context and always-on reasoning for coding, 3D creation, financial research, and agentic work.
Updated Nov 11, 2026. Default version: Kimi K3.1 Pro
LLMBoard Score88.5Kimi K3.1 Pro
Coverage20%30 benchmark families
Context window1MTokens
Official input price$2Moonshot AI API
Kimi K3.1 Pro Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Kimi K3.1 Pro Benchmark Results
Benchmark scores for Kimi K3.1 Pro.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAPEX-Agents | Score67.20% | Rank01 | Participants13 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkAutomationBench-AA | Score73.30% | Rank01 | Participants6 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkBabyVision | Score95.40% | Rank01 | Participants18 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkDeepSWE | Score75.50% | Rank01 | Participants14 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkHarvey's Legal Agent Benchmark | Score23.70% | Rank01 | Participants5 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkKimi Code Bench v2 | Score77.10% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro (with tools) | Score90.00% | Rank01 | Participants5 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkPerceptionBench | Score68.30% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score92.10% | Rank02 | Participants76 | Percentile98.67% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score84.10% | Rank02 | Participants76 | Percentile98.67% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam (with tools) | Score70.00% | Rank02 | Participants7 | Percentile83.33% | EvidenceC | Evaluated |
| BenchmarkGDPval-AA 2.1 | Score1,846.00 points | Rank02 | Participants8 | Percentile85.71% | EvidenceC | Evaluated |
| BenchmarkBenchCAD | Score72.80% | Rank03 | Participants8 | Percentile71.43% | EvidenceC | Evaluated |
| BenchmarkChartography | Score90.20% | Rank03 | Participants8 | Percentile71.43% | EvidenceC | Evaluated |
| BenchmarkExploitBench | Score74.70% | Rank03 | Participants9 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkGDP.pdf | Score34.60% | Rank03 | Participants15 | Percentile85.71% | EvidenceC | Evaluated |
| BenchmarkBenchCAD (with Python tool) | Score92.70% | Rank04 | Participants8 | Percentile57.14% | EvidenceC | Evaluated |
| BenchmarkBioMysteryBench | Score80.60% | Rank04 | Participants8 | Percentile57.14% | EvidenceC | Evaluated |
| BenchmarkAA-Briefcase v1.1 | Score1,678.00 points | Rank04 | Participants7 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkOfficeQA Pro | Score67.40% | Rank05 | Participants14 | Percentile69.23% | EvidenceC | Evaluated |
| BenchmarkSWE-Marathon | Score51.70% | Rank05 | Participants11 | Percentile60.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 4.0 | Score65.70% | Rank05 | Participants35 | Percentile88.24% | EvidenceC | Evaluated |
| BenchmarkExploitGym | Score20.70% | Rank06 | Participants11 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score94.20% | Rank06 | Participants265 | Percentile98.11% | EvidenceC | Evaluated |
| BenchmarkPostTrainBench | Score36.50% | Rank06 | Participants10 | Percentile44.44% | EvidenceC | Evaluated |
| BenchmarkZEROBench | Score0.39 points | Rank06 | Participants16 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkAgents' Last Exam | Score43.20% | Rank11 | Participants26 | Percentile60.00% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score89.00% | Rank11 | Participants64 | Percentile84.13% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench-Science 0.1 | Score38.10% | Rank11 | Participants12 | Percentile9.09% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score51.10% | Rank23 | Participants118 | Percentile81.20% | EvidenceC | Evaluated |
Kimi K3.1 Pro Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Kimi K3.1 Pro Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $2 input, $10 output per 1M
- Official provider
- Moonshot AI
- Lowest third-party
- From $1.9 input, $9.5 output per 1M via DevPass (LLM Gateway)
- Tracked offerings
- 30
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderKimi For Coding (kimi.com) | Provider model IDk3.1-pro | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderKimi For Coding (kimi.ai) | Provider model IDk3.1-pro | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDkimi-k3.1-pro | Regionglobal | Input / 1M$1.9 | Output / 1M$9.5 | Context1M | Updated |
| ProviderMoonshot AI (China) | Provider model IDkimi-k3.1-pro | Regionglobal | Input / 1M$1.94 | Output / 1M$10.17 | Context1M | Updated |
| ProviderMoonshot AI | Provider model IDkimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDmoonshot/kimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderPrime Inference | Provider model IDmoonshotai/kimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDmoonshotai/kimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDmoonshotai/kimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderOpenCode Go | Provider model IDkimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDmoonshotai/kimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderRequesty | Provider model IDkimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDmoonshotai/kimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderEden AI | Provider model IDmoonshot/kimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderVenice AI | Provider model IDkimi-k3-1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderNovita AI | Provider model IDmoonshotai/kimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderNEAR AI Cloud | Provider model IDmoonshotai/kimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderOfox | Provider model IDmoonshotai/kimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$11 | Context1M | Updated |
| ProviderBaseten | Provider model IDmoonshotai/Kimi-K3.1-Pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderTogether AI | Provider model IDmoonshotai/Kimi-K3.1-Pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| Providerai& | Provider model IDmoonshotai/kimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderEmpirioLabs AI | Provider model IDkimi-k3-1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderFireworks AI | Provider model IDaccounts/fireworks/models/kimi-k3p1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderOllama Cloud | Provider model IDkimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderDeep Infra | Provider model IDmoonshotai/Kimi-K3.1-Pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderCrossModel | Provider model IDmoonshot/kimi-k3.1-pro | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderCharm Hyper | Provider model IDkimi-k3.1-pro | Regionglobal | Input / 1M$2.2 | Output / 1M$11 | Context1M | Updated |
| Provider302.AI | Provider model IDkimi-k3.1-pro | Regionglobal | Input / 1M$2.4 | Output / 1M$12 | Context1M | Updated |
| ProviderMorph | Provider model IDmorph-kimik31 | Regionglobal | Input / 1M$2.5 | Output / 1M$14 | Context1M | Updated |
| ProviderTinfoil | Provider model IDkimi-k3-1-pro | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context262.1K | Updated |
Kimi K3.1 Pro Runtime Performance
Provider-specific output speed and catalog latency for Kimi K3.1 Pro. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Kimi K3.1 Pro Specifications
Technical details for the model's default version.
- Version
- Kimi K3.1 Pro
- Released
- Oct 23, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 2.8T
- Context window
- 1M
- Max output
- 1M
- Inputs
- image, text, video
- Outputs
- text
- Open weights
- Yes
- License
- Kimi K3.1 Pro License
Kimi K3.1 Pro 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 K3.1 Pro | Released | LLMBoard88.54 | Parameters2.8T | Context1M | Max output1M | Open weightsYes | LicenseKimi K3.1 Pro License |
Models similar to Kimi K3.1 Pro
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MA
Kimi K3
Moonshot AI
MA
Kimi K2.6
Moonshot AI
MA
Kimi K2.5
Moonshot AI
MA
Kimi K2.7 Code
Moonshot AI
MA
Kimi K2 Thinking
Moonshot AI
MA
Kimi K2
Moonshot AI
What is Kimi K3.1 Pro?
Key information about Kimi K3.1 Pro and its available data.
1 Pro is a multimodal LLM from Moonshot AI with a 1M context and always-on reasoning. It is described for coding, 3D creation, financial research, and agentic work.
Data as of 2026-11-10.
FAQ
Common questions about Kimi K3.1 Pro.
When was Kimi K3.1 Pro released?
Kimi K3.1 Pro's default version was released on Oct 23, 2026.
How much does Kimi K3.1 Pro cost?
Kimi K3.1 Pro's official API price is $2 per million input tokens and $10 per million output tokens via Moonshot AI. The lowest tracked third-party offer starts at $1.9 input and $9.5 output via DevPass (LLM Gateway).
Who created Kimi K3.1 Pro?
Kimi K3.1 Pro was created by Moonshot AI.
What is the context window for Kimi K3.1 Pro?
The default version has a 1M token context window.
Is Kimi K3.1 Pro open weight?
Yes. The default version is marked as open weight under Kimi K3.1 Pro License.