DeepSeek’s Flash-Class Vision Endpoint Keeps Screenshot Agents On-Platform
DeepSeek’s API changelog launched experimental DeepSeek-V4-Flash-Vision-Exp: images via base64, URL, or Files API file_id, on Chat Completions, Anthropic-compatible Messages, and Responses. Text-agent scores match official V4-Flash; DeepSeek says multimodal-agent results jump toward Claude Opus 4.8. Benchmarks are DeepSeek’s own. Distinct from the August 13 V4-Pro GA and price hike.
Corrected October 14, 2026: Corrected the test-settings line and removed an unsourced image-format list and claims that no independent listing existed. The benchmark table matches DeepSeek's changelog image.
DeepSeek’s V4 family has been text-agent priced. A Flash-class vision endpoint, on the same three API dialects, is how Hangzhou keeps OpenClaw/Codex-style harnesses from routing screenshots to Gemini or GPT-5.6.
DeepSeek added DeepSeek-V4-Flash-Vision-Exp to the API (model='deepseek-v4-flash-vision-exp'). Images via base64, public URL, or Files API file_id. Surfaces: Chat Completions, Anthropic-compatible Messages, and Responses. DeepSeek: pure-text agent/reasoning matches official V4-Flash; on vision-required agent benches the experimental model “delivers a significant leap,” “close to Opus-4.8.” The benchmark claims are DeepSeek's own.
Lab benches (changelog)#
| Bench | V4-Flash-Vision-Exp |
|---|---|
| Terminal Bench 2.1 | 83.9 |
| NL2Repo | 57.7 |
| DeepSWE | 59.3 |
| DSBench-Hard | 63.6 |
| AutomationBench (Public) | 25.7 |
| ApexBench (Pass@1) | 36.5 |
| Agents' Last Exam | 27.3 |
| Chartography | 64.3 |
| ZeroBench (Pass@5) | 35.0 |
Text-agent numbers used DeepSeek Harness Minimal Mode, max tokens set to the maximum, top_p 0.95, temperature 1.0. ApexBench and Agents' Last Exam: the text V4-Flash ignores multimodal elements — so those two are not a vision-vs-text comparison.
Independent rankings: none cited.
This is a new multimodal experimental SKU.
Limits#
- Vision “close to Opus-4.8” is lab-claimed.
- Launch billing: up to 384 tokens per image at V4-Flash rates; post-experimental pricing is open.
- Chartography 64.3 has not been independently re-run on images.
Sources#
- DeepSeek API changelog: V4-Flash-Vision-Exp (August 21, 2026) — benchmark table image
- DeepSeek Vision guide
- Times of AI:
deepseek-v4-api-pricing(August 13)