EXAONE
EXAONE is LG Research's image to text model. A multimodal LLM from LG AI Research capable of understanding images and generating detailed textual descriptions without losing visual information.
lgresearch-exaone |
| Image to Text |
| Active |
| LG Research |
| Image |
| Text |
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 |
|---|---|---|---|---|---|
| EXAONE 4.5 33B | — | — | — | — | Available |
| EXAONE 4.0 32B Reasoning | — | — | — | — | Available |
| EXAONE 4.0 32B | — | — | — | — | Available |
| EXAONE 4.1 2B Reasoning | — | — | — | — | Available |
| EXAONE 4.1 2B | — | — | — | — | Available |
| EXAONE | — | — | — | — | Current |
| K-EXAONE | — | — | — | — | Available |
| K-EXAONE Non-Reasoning | — | — | — | — | Available |