LongCat 2.0
3609°
Run this model
Offers / Ads
Meituan | 1,048,756 token context | $0.30/M input, $1.20/M output. LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic workflows.
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?
Open weights vs open source vs API-only: what you are actually allowed to do
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
LongCat 2.0 is a sparse mixture-of-experts model from Meituan, activating 48B of its 1.6T parameters per token and trained on over 35 trillion tokens with a native 1M-token context window. Its architecture is purpose-built for long-horizon tasks: repository-level code changes, agentic workflows, and sustained reasoning over very long inputs. Open weights and a modest API price make it worth a look if you work at the frontier of context length.
Known for
- Native 1M-token context, trained on hundreds of billions of long-context tokens
- Strong fit for repository-level code edits and agentic task execution
- Integrates directly with Claude Code, OpenClaw, and Hermes harnesses
- Novel LongCat Sparse Attention reduces the cost of attending over massive contexts
- Open weights available on Hugging Face
Watch out for
- 1.6T total parameters means local deployment requires serious hardware; most users will hit the API.
- Benchmarks in the model card are measured in-house, so independent third-party comparisons are limited.
- Licence terms are not detailed in the published information; check the Hugging Face repository before commercial use.
Prompts to try
Refactor across a repo
Here is a Python repository with three files. The codebase currently uses a global config dict passed as a function argument everywhere. Refactor it to use a typed dataclass injected via a context manager, update all call sites, and write a brief migration note explaining what changed and why.
Long document reasoning
I am pasting a 200-page technical specification below. Read it in full, then answer: what are the three most significant design trade-offs the authors made, what evidence in the document supports each, and what would you change if you were revising the spec today?
Multi-step agent plan
You are helping automate a software release pipeline. Given these steps: run tests, build a Docker image, push to a registry, update a Helm chart, and open a pull request, write a dependency graph, identify which steps can run in parallel, and produce a shell script that executes them in the correct order with error handling.
Compare with
- GPT-6 LunaAPI-only model1,050,000 token context · $0.10/M input, $0.50/M output
- Claude Opus 5.5API-only model1,000,000 token context · $4.00/M input, $20.00/M output
- Muse Spark 1.3 ContributorAPI-only model1,048,576 token context · $0.10/M input, $0.20/M output
- Gemini 3.8 FlashAPI-only model1,048,576 token context · $0.83/M input, $4.12/M output
More text models from meituan
Questions people ask
- Are the weights open and can I run LongCat 2.0 locally?
- Yes, the weights are publicly available on Hugging Face under the meituan-longcat/LongCat-2.0 repository. With 1.6T total parameters it is a large model, so local deployment demands substantial hardware.
- What does LongCat 2.0 cost and what is its context window?
- Via the API it is $0.30 per million input tokens and $1.20 per million output tokens, with a context window of just over 1 million tokens.
- How is LongCat 2.0 different from other large MoE models?
- Its main differentiator is the LongCat Sparse Attention mechanism, which is designed specifically to make attending over very long contexts efficient, combined with training on hundreds of billions of 1M-context tokens — something most comparable MoE models have not done at this scale.
Captain's verdictA serious long-context MoE that earns its place if your work lives in large codebases or documents that break every other model's context limit.
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.
LongCat 2.0 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