LongCat-2.0
LongCat-2.0 is Meituan’s language model for conversations through its official chat service, with options to run it using GPUs or NPUs. Summary written by AI Index from Meituan’s own pages.
- In Input modalities: Text Out Output modalities: Text
- Reasoning
- Reasoning can be off
- Tool use
- Open weights
Prices
2 offerings · prices as listedLongCat-2.0| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | $0.30 | $0.006 | $1.20 |
Prices from LongCat API: pricing (LongCat-2.0) (opens in a new tab) (checked Nov 9, 2026)
LongCat-2.0| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | ¥2.00 | ¥0.040 | ¥8.00 |
Prices from LongCat API: pricing (LongCat-2.0) (opens in a new tab) (checked Nov 9, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Licence
- MIT License
- Family
- longcat
- Model ID
Not stated on Meituan’s pages: max input, reasoning efforts, max thinking budget, structured output, built-in tools, knowledge cutoff, aliases.
Run locally
Weights: meituan-longcat/LongCat-2.0- Parameters 1.78T
- Active 48B · 768 experts, 12 per token
- Native precision BF16
- Layers 38
- KV cache per token 43 KB
- Config positions 256K (config.json max_position_embeddings)
- API context 977K (maker’s API)
- Needs
- ≈ 922.7 GB (weights 878.5 + KV cache 0.3 + overhead 43.9)
- Usable
- 21.6 GB (90% of its memory)
- Try
- it’s too large for this hardware; see the smallest that runs it below
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 3307.8 GB | ≈ 3473.5 | ✕Doesn’t fit | — |
| Q8_0 | 1757.0 GB | ≈ 1845.2 | ✕Doesn’t fit | — |
| INT8 (GPTQ)maker’s file | 1918.7 GB | ≈ 2015.0 | ✕Doesn’t fit | — |
| FP8maker’s file | 1910.3 GB | ≈ 2006.2 | ✕Doesn’t fit | — |
| Q6_K | 1358.0 GB | ≈ 1426.3 | ✕Doesn’t fit | — |
| Q5_K_M | 1176.1 GB | ≈ 1235.3 | ✕Doesn’t fit | — |
| Q5_0 | 1136.9 GB | ≈ 1194.0 | ✕Doesn’t fit | — |
| Q4_K_M | 1004.6 GB | ≈ 1055.1 | ✕Doesn’t fit | — |
| Q4_0 | 930.2 GB | ≈ 977.0 | ✕Doesn’t fit | — |
| IQ4_XS | 878.5 GB | ≈ 922.7 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 808.2 GB | ≈ 849.0 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 632.5 GB | ≈ 664.5 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 620.1 GB | ≈ 651.4 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 425.8 GB | ≈ 447.4 | ✕Doesn’t fit | — |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): no single listed machine; about 15 × 80 GB GPUs.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-21. How it’s estimated
Cited scores
From third-party leaderboards, not measured by usThis model isn’t on any leaderboard we cite yet.
Changes
All changes →- Output price cut 60% ¥20.00 → ¥8.00 / 1M tokens · LongCat API, China
- Cache read price cut 60% ¥0.10 → ¥0.040 / 1M tokens · LongCat API, China
- Input price cut 60% ¥5.00 → ¥2.00 / 1M tokens · LongCat API, China
- Output price cut 59.3% $2.95 → $1.20 / 1M tokens · LongCat API
- Cache read price cut 60% $0.015 → $0.006 / 1M tokens · LongCat API
- Input price cut 60% $0.75 → $0.30 / 1M tokens · LongCat API
Sources
- LongCat API: pricing (LongCat-2.0) (opens in a new tab) longcat.chat · checked Nov 9, 2026
- LongCat API: quick start (opens in a new tab) longcat.chat · checked Oct 26, 2026
- LongCat API: chat completions (opens in a new tab) longcat.chat · checked Nov 9, 2026
- Change Log | LongCat API Docs (opens in a new tab) longcat.chat · checked Nov 8, 2026
- meituan-longcat/LongCat-2.0 model card (opens in a new tab) huggingface.co · checked Nov 8, 2026
- meituan-longcat/LongCat-2.0 model card (opens in a new tab) huggingface.co · checked Nov 8, 2026
- GitHub - meituan-longcat/LongCat-2.0 · GitHub (opens in a new tab) github.com · checked Nov 4, 2026
- meituan-longcat/LongCat-2.0 model card (opens in a new tab) huggingface.co · checked Nov 6, 2026
- meituan-longcat/LongCat-2.0 files (opens in a new tab) huggingface.co · checked Nov 6, 2026
- meituan-longcat/LongCat-2.0-FP8 files (opens in a new tab) huggingface.co · checked Nov 7, 2026
- meituan-longcat/LongCat-2.0-INT8 files (opens in a new tab) huggingface.co · checked Nov 4, 2026
- meituan-longcat/LongCat-2.0 config.json (opens in a new tab) huggingface.co · checked Nov 7, 2026
- meituan-longcat/LongCat-2.0 README.md (opens in a new tab) huggingface.co · checked Nov 5, 2026
Meituan · China · longcat.chat
Related models
Snapshots, the same family and other models from this provider