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.
Routable on MiniRouter
Use deepseek/deepseek-v4-flash-vision-exp via the API →- 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 release announcement 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 are grouped by unit. Percentage, Elo, and task-count results never share a scale.
| 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 runs its own evaluations and timing against each model's first-party API. These are the only numbers on this page not reported by the publisher.
DeepSeek V4 Flash Vision (reasoning max) ranks #30 of 448 model families on their Intelligence Index.
- Intelligence Index
- 51.5
- 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
- 111
- Median tokens per second
- First answer token
- 19s
- Median seconds, including reasoning
DeepSeek V4 Flash Vision (reasoning max) on Artificial Analysis ↗
Source: Artificial Analysis ↗, read Sep 2, 2026. Measured on the model's first-party API, not a MiniRouter route.
What is not independently confirmed
- Every figure on this page is self-reported by the cited publisher. MiniRouter did not run these benchmarks.
- Benchmark harnesses are not standardised. Results sharing a name across vendors have not been confirmed to use identical runs.
- Publisher pricing can change, and introductory phases have stated end dates.
- DeepSeek-V4-Flash-Vision-Exp is routable through MiniRouter today; live pricing on its model page is authoritative over the publisher figures here.
Related coverage
Other release dossiers and the current MiniRouter catalog.
Sources
- Read at DeepSeek ↗
DeepSeek model card
Published Aug 21, 2026
- Read at Artificial Analysis ↗
Artificial Analysis model page
Published Sep 2, 2026
Editorial reference revised 2026-09-02. Catalog status comes from the generated routing snapshot.