DeepSeek V4 Flash Vision Exp
deepseek-flash
Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work
ReasoningTool CallingAttachmentsStructured Output
Context Window
1M
Max Output
384K
Temperature
Yes
Open Weights
No
Knowledge Cutoff
N/A
Released
2026-08-21
Last Updated
2026-08-21
Modalities
Input:TextImage
→Output:Text
Available Providers (9)
| Provider | Input /1M | Output /1M | Cache Read /1M | Cache Write /1M | Reasoning | Status |
|---|---|---|---|---|---|---|
| Rp 2.603 | Rp 5.223 | Rp 355 | — | toggle, effort | — | |
| Rp 3.895 | Rp 11.684 | Rp 124 | — | effort | — | |
| Rp 3.895 | Rp 11.684 | Rp 124 | — | toggle, effort | — | |
| Rp 7.170 | Rp 21.510 | Rp 239 | Rp 7.170 | toggle, effort | — | |
| Rp 2.479 | Rp 4.957 | Rp 50 | — | effort | — | |
| Rp 7.790 | Rp 23.368 | Rp 248 | — | toggle, effort | — | |
| Rp 3.895 | Rp 11.684 | Rp 124 | — | toggle, effort | — | |
| Rp 3.895 | Rp 11.684 | Rp 124 | — | effort | — | |
| Rp 3.895 | Rp 11.684 | Rp 124 | — | effort | — |