LongCat 2.0
Meituan · released Jul 5, 2026 · meituan-longcat/LongCat-2.0
- Type
- Open weightsMIT License
- Params
- 1.8T
- Context
- 1M
active per word not recorded by us · about 787K words of context
Our take
Written Sep 2, 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 very long documents, though no benchmark scores have been published to verify its quality.
Pick this when you need a genuinely permissive licence and a context window above one million tokens, or when you want identical pricing across both tracked providers. Skip it if you need verified quality scores, fast throughput, or any multimodal input.
The case for it
- One-million-token request limit among the largest we hold for any downloadable text model.
- MIT licence allows commercial use, modification and redistribution with minimal restrictions.
- Identical pricing across both tracked providers, so provider choice comes down to speed and support.
The case against it
- No benchmark scores in our data — chat, reasoning and coding capabilities are unverified.
- 1.8 trillion total parameters with no disclosed active count; inference cost and speed implications are unclear.
- Only one provider discloses throughput, at 32 tokens per second.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
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.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 2 hours ago — each listing carries its own date.
- 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 |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.30 / $1.20checked 2 hours ago | 1M | not measured | Unknown | Unknown | Unknown |
| AtlasCloudfp8Through OpenRouter | $0.30 / $1.20checked 2 hours ago | 1M262K max reply | 48 tok/s | No | Yesunknown period | Unknown |
Across the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✗ | ✗ |
| AtlasCloudfp8Through OpenRouter | ✓ | ✗ | ✗ |
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
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
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 independent board has scored it, so we hold no quality figures at all.
- We do not hold the active parameter count for it, so how much of it runs on any one token is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
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
- Takes in, gives back
- Text in, text out
- Catalogue slug
- meituan-longcat-2-0