Meituan
LongCat-2.0
Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window
Model facts
- Context window
- 1.05M tokens
- Maximum output
- 262K tokens
- Cheapest paid input
- $0.3 per 1M tokens
- Cheapest paid output
- $1.2 per 1M tokens
- Open weights
- yes
- Providers
- 6
Capabilities and modalities
reasoning, tool calling, structured output, temperature control, open weights, text.
Local hardware estimate
At 4K context: Q4_K_M 1087.7 GiB, Q8_0 1914.5 GiB, F16 3464.8 GiB working memory.
- Parameters
- 1775.6 billion
- Architecture
- longcatcausallm
- Model license
- mit
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| default | 34.0 | 45.3 | not measured | 40.5 |
Observed price history
- 2026-08-24: $0.3 input / $1.2 output per 1M tokens
- 2026-09-01: $0.3 input / $1.2 output per 1M tokens
API providers
- OpenCode Go — model id longcat-2.0; $0.3 input / $1.2 output per 1M tokens; provider documentation
- OpenRouter — model id meituan/longcat-2.0; $0.3 input / $1.2 output per 1M tokens; provider documentation
- LongCat — model id LongCat-2.0; $0.75 input / $2.95 output per 1M tokens; provider documentation
- Kilo Gateway — model id meituan/longcat-2.0; $0.75 input / $3 output per 1M tokens; provider documentation
- NanoGPT — model id longcat-2.0; $0.75 input / $3 output per 1M tokens; provider documentation
- Arena — model id longcat-2.0; not published input / not published output per 1M tokens; provider documentation