Blended multimodal model that runs multiple language models in parallel and returns a synthesized answer
Details
| Field | Value |
|---|---|
| id | unbiased/pareto |
| modality | text+image->text |
| context_length | 262144 |
| max_output_tokens | 131072 |
| release_date | 2026-09-17 |
| is_open_weights | no |
| supports_tool_call | yes |
| supports_reasoning | no |
| supports_structured_output | no |
| supports_attachment | yes |
| input_modalities | text, image |
| output_modalities | text |