LongCat Flash Lite
LongCat Flash Lite is Meituan's language model. A lightweight variant of Meituan's LongCat Flash model designed for efficient inference with reduced resource requirements.
| Benchmarks | |
|---|---|
| Intelligence Index | #277 |
| GPQA | #320 |
| HLE | #334 |
| IFBench | #235 |
| Time to First Token | #197 |
| SciCode | #338 |
| LCR | #312 |
| TerminalBench Hard | #218 |
| TAU2 | #125 |
| Output TPS | #431 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| LongCat Flash Thinking | 33K | — | — | Available | |
| LongCat Flash Chat | 128K | — | — | Available | |
| LongCat Flash Lite | — | — | — | — | Current |
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| LongCat 2.0 | — | 1.0M | $0.300 | $1.20 | |
| LongCat Image | — | — | — | — | — |