Kimi K2 0711
4608°
Run this model
Offers / Ads
MoonshotAI | 131,072 token context | $0.57/M input, $2.30/M output. Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.
Guides for this model
Best local LLM by use case (October 2026): the right open model for every job
How much VRAM do I actually need for local AI?
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
Kimi K2 Instruct is Moonshot AI's 1-trillion-parameter MoE model, activating 32 billion parameters per forward pass and trained on 15.5 trillion tokens using the MuonClip optimizer for stable large-scale training. It is built specifically for agentic work: tool use, autonomous coding, and multi-step reasoning rather than extended chain-of-thought. Open weights are available, and API pricing is modest for a model at this scale.
Known for
- Top-tier agentic coding on SWE-bench Verified, competitive with Claude Sonnet 4.
- Strong tool-use scores on Tau2 and AceBench across retail, airline, and telecom tasks.
- 128K token context window for long document and codebase work.
- Open weights on Hugging Face under moonshotai/Kimi-K2-Instruct.
- MoE architecture: 1T total parameters, only 32B active per token — efficient at inference.
Watch out for
- This is a reflex-grade instruct model with no extended thinking mode; for deep chain-of-thought, look elsewhere.
- At 1T total parameters, self-hosting requires serious hardware — quantised GGUF versions are your practical local option.
- Licence terms for commercial use are not detailed here; check the Hugging Face repository before deploying.
Prompts to try
Debug a failing agent loop
I have a Python agent that calls a search tool, parses the result, then decides whether to call it again. After two iterations it always exits early, even when the stopping condition is not met. Here is the code: [paste your code]. Identify the bug, explain why it causes early exit, and show the corrected version with a brief explanation of the fix.
Solve a logic constraint puzzle
Five engineers — Ada, Ben, Cara, Dan, and Eve — each own exactly one of five laptops: A, B, C, D, E. Ada does not own A or B. Ben owns a higher-lettered laptop than Cara. Dan owns D. Eve does not own C. No two people share a laptop. Who owns which laptop? Show your reasoning step by step.
Design a multi-tool workflow
You have three tools: search(query), fetch_page(url), and summarize(text). A user asks: 'What are the three most-cited papers on mixture-of-experts scaling published after 2022?' Write out the exact sequence of tool calls you would make, what you expect each to return, and how you would combine the results into a final answer.
Compare with
- Kimi K3Open-weights model1,048,576 token context · $0.30/M input, $11.94/M output
- Kimi K2 ThinkingOpen-weights model262,144 token context · $0.60/M input, $2.50/M output
- Kimi K2.7 CodeOpen-weights model262,144 token context · $0.67/M input, $3.35/M output
- Kimi K2.5Open-weights model262,144 token context · $0.50/M input, $2.50/M output
More text models from moonshotai
Questions people ask
- Are the weights open and can I run Kimi K2 locally?
- Yes — weights are published on Hugging Face at moonshotai/Kimi-K2-Instruct. With 1 trillion total parameters you will need quantised versions (GGUF or similar) and substantial VRAM or RAM to run it locally.
- What does Kimi K2 cost via API and what is the context window?
- Moonshot AI prices it at $0.57 per million input tokens and $2.30 per million output tokens, with a 128K token context window.
- How does Kimi K2 Instruct differ from Kimi K2 Base?
- The Base model is the raw pre-trained checkpoint intended for researchers who want to fine-tune or build custom solutions. The Instruct model is post-trained for direct use in chat and agentic pipelines, with no extended thinking mode.
Captain's verdictA serious open-weights agentic model that punches above its API price on coding and tool-use tasks — worth testing before defaulting to Claude or GPT-4.1.
Model card on Hugging Face
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
How this score adds up
This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
Kimi K2 0711 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153