Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work
Details
| Field | Value |
|---|---|
| id | accounts/fireworks/models/deepseek-v4-flash-vision-exp |
| family | deepseek-flash |
| modality | text+image->text |
| context_length | 1000000 |
| max_output_tokens | 384000 |
| release_date | 2026-08-21 |
| is_open_weights | yes |
| supports_tool_call | yes |
| supports_reasoning | yes |
| supports_structured_output | yes |
| supports_attachment | yes |
| input_modalities | text, image |
| output_modalities | text |