LongCat 2.0
Meituan · released Jul 5, 2026 · meituan-longcat/LongCat-2.0
- Type
- Open weightsMIT License
- Params
- 1.8T
- Context
- 1M
about 787K words of context
Our take
Written Aug 3, 2026LongCat 2.0 is a 1.8-trillion-parameter text model from Meituan with a permissive MIT licence and a one-million-token request limit. It is built for long-document work and research use, though no benchmark scores have been published and only two hosts currently offer it.
Pick this when you need a genuinely permissive licence and a one-million-token context window for long-document processing, or when you want downloadable weights for research and modification. Use it if Atlas Cloud's reported throughput meets your latency needs. Skip it if you need measured quality data, multimodal input, a wide choice of providers, or if you are unsure whether 28 tokens per second is fast enough for your workload.
The case for it
- One-million-token request limit, among the largest we catalogue.
- MIT licence allows commercial use, modification and redistribution with minimal restrictions.
- 1,775.6 billion total parameters.
The case against it
- No benchmark scores in our data — chat, reasoning, coding and other capabilities are all unverified.
- Only two tracked offers, identically priced, so there is no price competition and provider choice is limited.
- Throughput is modest or unverified: Atlas Cloud reports 28 tokens per second, while OpenRouter's figure is undisclosed in our data.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up LongCat 2.0 — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Radeon RX 7900 XT · 20 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 2 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.30 in / $1.20 out
- Context served
- 1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.30 / $1.20 | 1M | not measured | Unknown | Unknown | Unknown |
| AtlasCloudfp8 | $0.30 / $1.20 | 1M | 36 tok/s | No | Yesunknown period | Unknown |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✗ | ✗ |
| AtlasCloudfp8 | ✓ | ✗ | ✗ |
Tool calling: 2 of 2 listings say yes. JSON output: 0 of 2 listings say yes, 2 say no. Strict schema: 0 of 2 listings say yes, 2 say no.
When we formed this view
Dates behind this page
Prices last checked 13h ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No board we watch has turned up a score, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsMIT License, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
MIT License
Fully permissive: do anything with attribution. No patent grant, unlike Apache-2.0.
Identifiers
- Hugging Face
- meituan-longcat/LongCat-2.0
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- meituan-longcat-2-0