DeepSeek-V4-Flash-Vision-Exp
DeepSeek's first experimental multimodal V4 model, adding visual modules and continued training to V4-Flash at V4-Flash pricing, with publisher-reported agent results DeepSeek places close to Claude Opus 4.8.
DeepSeek-V4-Flash-Vision-Exp is available on MiniRouter as . The model page has current pricing, provider routes and API setup.
About the model
- Context: 1M. 1,048,576 positions per the published config
- Off-peak discount: 50% off peak. Peak is 01:00–04:00 and 06:00–10:00 UTC on weekdays; cache hits bill $0.014 at peak
- Vision input: Up to 600 images. JPEG, PNG, GIF, or WebP in user messages, up to 384 tokens each
- Weights: Released. MIT license on Hugging Face; about 305B parameters
Publisher pricing
Pricing below comes from the linked publisher sources and does not represent a MiniRouter route or price.
| Phase | Input / 1M | Output / 1M | Blended / 1M | Effective | Source |
|---|---|---|---|---|---|
| Standard · peak | $0.44 | $1.32 | $0.66 | Aug 21, 2026 – open-ended | DeepSeek ↗ |
Publisher-reported benchmarks
Results from the publisher’s announcement, grouped by unit.
| Benchmark | Reported result | Reported by | As of | Source |
|---|---|---|---|---|
| Terminal Bench 2.1 | 83.9 | DeepSeek | Aug 21, 2026 | Announcement ↗ |
| DeepSWE | 59.3 | DeepSeek | Aug 21, 2026 | Announcement ↗ |
| CyberGym | 75.3 | DeepSeek | Aug 21, 2026 | Announcement ↗ |
| NL2Repo | 57.7 | DeepSeek | Aug 21, 2026 | Announcement ↗ |
| Toolathlon Verified | 75.9 | DeepSeek | Aug 21, 2026 | Announcement ↗ |
| DSBench-Hard | 63.6 | DeepSeek | Aug 21, 2026 | Announcement ↗ |
| ApexBench · pass@1 | 36.5 | DeepSeek | Aug 21, 2026 | Announcement ↗ |
| Agents' Last Exam | 27.3 | DeepSeek | Aug 21, 2026 | Announcement ↗ |
| Chartography | 64.3 | DeepSeek | Aug 21, 2026 | Announcement ↗ |
DeepSeek says the model matches V4-Flash on text agents, reasoning, and knowledge while bringing multimodal agent performance close to Opus 4.8.
DeepSeek labels the release experimental; the earlier non-vision V4-Flash ignored image content in prompts.
DeepSeek reports the benchmark figures; MiniRouter has not reproduced them.
Independent measurements
Artificial Analysis evaluations of the first-party API.
DeepSeek V4 Flash Vision (reasoning max) ranks #31 of 462 model families on their Intelligence Index.
- Intelligence Index
- 34.8
- Composite of their evaluations
- Coding Index
- 65.0
- Coding evaluations only
- Blended price
- $0.66
- USD per 1M tokens, 3:1 input to output, first-party list
- Output speed
- 238
- Median tokens per second
- First answer token
- 9.3s
- Median seconds, including reasoning
DeepSeek V4 Flash Vision (reasoning max) on Artificial Analysis ↗
Source: Artificial Analysis ↗, read Sep 21, 2026. Measured on the model's first-party API, not a MiniRouter route.
Keep exploring
Compare published results in the model rankings and coding benchmarks, or read more model releases.
For MiniRouter product updates, visit the changelog.
Sources
- Read at DeepSeek ↗
DeepSeek model card
Published Aug 21, 2026
- Read at DeepSeek ↗
DeepSeek API pricing
Published Aug 21, 2026
- Read at Artificial Analysis ↗
Artificial Analysis model page
Published Sep 21, 2026
Editorial reference revised 2026-10-23. Catalog status comes from the generated routing snapshot.