DeepSeek
DeepSeek V4 Flash Vision Exp
Launched 2026-08-21 · Listed on OpenRouter 2026-08-21
Prices updated . Benchmarks updated .
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...
You send / 1M
$0.440
tokens in
It replies / 1M
$1.32
tokens out
Context
1M
tokens it can read at once
Typical request
$0.0012
1,000 words in, 400 out
Benchmarks
No independent score in the current Epoch or LMArena files, and no lab-reported score on file.
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DeepInfra · fp8 | $0.172 | $0.517 | 0% | Read |
| DeepInfra · fp8 | $0.216 | $0.647 | 99% | Read |
| DeepInfra · fp8 | $0.323 | $0.970 | 97% | Read |
| SiliconFlow · fp8 | $0.440 | $1.32 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text, image
- Writes: text
- Weights: Open weights
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 384K tokens
- Repeated text is billed at $0.014 per 1M (prompt caching)
Compare with
Appears in
Estimate your monthly cost with DeepSeek V4 Flash Vision Exp
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.
