moonshotai
MoonshotAI: Kimi K3.1 Pro
moonshotai/kimi-k3.1-pro
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Kimi K3.1 Pro (moonshotai/kimi-k3.1-pro) is Moonshot AI's open-weight, natively multimodal agentic model, post-trained from Kimi K3 with large-scale joint reinforcement learning. Per its model card, it uses a mixture-of-experts architecture with a dedicated vision encoder and a context window of roughly one million tokens; the OpenRouter catalog lists text, image and video inputs with text output. Vendor-reported evaluations show competitive coding and agentic results at maximum reasoning effort, though outcomes are mixed on some benchmarks.[1][2]
Strengths
- Source-described as an open-weight mixture-of-experts model with a roughly one-million-token context window, suited in principle to very long inputs.[1][2]
- Reasoning is enabled by default and configurable across several effort levels, according to the OpenRouter catalog listing.[1]
- Measured results in the supplied sources are competitive on several vendor-run coding, agentic and multimodal benchmarks, and the catalog's design-arena data shows relatively strong outcomes in areas such as UI component and 3D generation.[1][2]
Limitations
- Evidence gaps: the benchmark table in the source pack is truncated, and knowledge cutoff, deployment hardware requirements and safety behavior are not documented; the license is listed only as a custom 'other' license, so terms should be reviewed before use.[2]
- Reported evaluations were run at maximum reasoning effort with specific sampling settings and include internal benchmarks, so results may not generalize to other configurations; some scores trail listed peers, particularly on certain program-synthesis and science-terminal tasks.[2]
- Input modality is inconsistent across sources: the model card's summary table lists text and image, while OpenRouter additionally lists video input, so video support should be verified before relying on it.[1][2]
Where to use it
- Worth evaluating for long-horizon coding and agentic workflows that benefit from a very large context window and tool use, given the vendor's stated focus and reported benchmark results.[1][2]
- May suit design-oriented generation tasks such as UI components, SVG or 3D assets, where catalog arena data shows relatively strong outcomes; validate quality on your own workload.[1]
- Candidate for research and analysis tasks such as financial research, which the vendor cites as an improved area, subject to independent accuracy checks.[2]
Sources
- [1] OpenRouter catalog · MoonshotAI: Kimi K3.1 ProSources checked: Nov 13, 2026
- [2] Model documentation · MoonshotAI: Kimi K3.1 ProSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...
Specifications
- Model ID
- moonshotai/kimi-k3.1-pro
- Canonical ID
- moonshotai/kimi-k3.1-pro-20261023
- Creator
- moonshotai
- Added to OpenRouter
- 23.10.2026
- Context length
- 1,048,576
- Modality
- text+image+video->text
- Input modalities
- text, image, video
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $2 / out $10
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | AA — next 20% of the cohort | reasoning: optional · default max · efforts: max, high, low, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default max · efforts: max, high, low, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | input: video |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 46.5 | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | agents · androidnativewin rate 42.6% · rank 28 | 1,149Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · codetovideowin rate 58.5% · rank 5 | 1,232Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | agents · fullstackwin rate 61.9% · rank 2 | 1,327Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · mobileappswin rate 59.7% · rank 4 | 1,273Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · pdfwin rate 57.3% · rank 12 | 1,226Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · python-pptxslideswin rate 67.3% · rank 3 | 1,292Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · webappswin rate 61% · rank 3 | 1,307Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · 3dwin rate 70.8% · rank 3 | 1,447Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · asciiartwin rate 59.1% · rank 6 | 1,302Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 60.8% · rank 7 | 1,351Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · datavizwin rate 56% · rank 13 | 1,304Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 66.1% · rank 4 | 1,406Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 62.6% · rank 2 | 1,329Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 65.4% · rank 1 | 1,388Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 57.9% · rank 6 | 1,323Elo | SS — top 10% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Relacefp4 | 1,048,576 | $0.237 | $8.41 | — | — | 100% |
| Wafermxfp4 | 1,048,576 | $0.253 | $8.8 | — | — | 100% |
| Morphfp8 | 1,048,576 | $0.871 | $11.11 | — | — | 100% |
| Sail Researchfp4 | 1,048,576 | $1.04 | $9.35 | — | — | 100% |
| Sail Researchfp4 | 1,048,576 | $1.4 | $9.35 | — | — | — |
| AkashMLfp4 | 1,048,576 | $1.75 | $10 | — | — | 100% |
| Decartmxfp4 | 409,600 | $1.76 | $8.8 | — | — | 100% |
| Wafermxfp4 | 1,048,576 | $1.8 | $9 | — | — | 100% |
| InferenceNetmxfp4 | 1,048,576 | $1.8 | $9 | — | — | 100% |
| InferenceNetmxfp4 | 1,048,576 | $1.8 | $9 | — | — | 100% |
| DeepInfrabf16 | 1,048,576 | $1.9 | $9.5 | — | — | 100% |
| River | 1,048,576 | $2 | $10 | — | — | 100% |
| Fireworks | 1,048,576 | $2 | $10 | — | — | 100% |
| DigitalOcean | 1,048,576 | $2 | $10 | — | — | 100% |
| Parasailfp4 | 1,048,576 | $2 | $10 | — | — | 100% |
| Modalmxfp4 | 1,048,576 | $2 | $10 | — | — | 100% |
| Nebiusfp4 | 1,048,576 | $2 | $10 | — | — | 68.42% |
| Together | 1,048,576 | $2 | $10 | — | — | 15% |
| Moonshot AImxfp4 | 1,048,576 | $2 | $10 | — | — | 100% |
| Alibaba | 1,048,576 | $2.3 | $11.5 | — | — | 100% |
| PrimaLabsmxfp4 | 1,048,576 | $2.7 | $13.5 | — | — | 100% |
| InferenceNetmxfp4 | 1,048,576 | $2.7 | $13.5 | — | — | 100% |
| InferenceNetmxfp4 | 1,048,576 | $2.7 | $13.5 | — | — | 100% |
| Moonshot AImxfp4 | 1,048,576 | $4 | $20 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.