DeepSeek · Released Aug 21, 2026
DeepSeek V4 Flash Vision Exp
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text…
- Released
- Aug 21 2026
- Context window
- 1M 262K out
- Input / 1M tokens
- $0.22 from Free
- Output / 1M tokens
- $0.65 from Free
Where to run it
16 providers compared
Free to try on AMD — free endpoints are often limited-time and rate-limited. Cheapest: OpenCode at $0.14 / $0.28 per 1M input / output tokens — 80% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| AMDfree · may be limited-time | Free | Free | Free | 1M | 384K | — | Free |
| OpenCode | $0.14 | $0.28 | $0.028 | 1M | 384K | — | Cheapest |
| CommandCode | $0.15 | $0.60 | $0.003 | 1M | 384K | — | +50% |
| Eden AI | $0.15 | $0.60 | $0.003 | 1M | 384K | — | +50% |
| AIHubMix | $0.15 | $0.62 | $0.003 | 1M | 384K | — | +55% |
| DeepInfraFP8 | $0.22 | $0.65 | $0.007 | 1M | 262K | 100%24h | +85% |
| NanoGPT | $0.22 | $0.65 | $0.007 | 1M | 384K | — | +85% |
| Kilo Gateway | $0.22 | $0.65 | $0.007 | 1M | 262K | — | +85% |
| Vercel AI Gateway | $0.22 | $0.65 | $0.007 | 1M | 1M | — | +85% |
| OrcaRouter | $0.22 | $0.66 | $0.007 | 1M | 384K | — | +89% |
| CrossModel | $0.30 | $1.20 | $0.006 | 1M | 384K | — | +200% |
| SiliconFlowFP8 | $0.44 | $1.32 | $0.028 | 1M | 393K | 100%24h | +277% |
| GMICloudFP8 | $0.44 | $1.32 | $0.014 | 1.05M | 944K | 99.7%24h | +277% |
| Hugging Face | $0.44 | $1.32 | — | 1M | 384K | — | +277% |
| Ofox | $0.44 | $1.32 | $0.014 | 1M | 384K | — | +277% |
| AI/ML API | $0.57 | $1.72 | $0.018 | 1M | 384K | — | +390% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated DeepSeek V4 Flash Vision Exp. Scores appear here automatically once it does.
Specs
Details
- Model ID
deepseek/deepseek-v4-flash-vision-exp- Developer
- DeepSeek
- Release date
- Aug 21, 2026 ·
- Context window
- 1,048,576 tokens
- Max output
- 262,144 tokens
- API price
- $0.22 / $0.65 per 1M input / output tokens
- Providers
- 16
- Input types
- text, image
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.