DeepSeek
RankedEnough results for an index.DeepSeek V4 Flash Vision Exp
DeepSeek V4 Flash Vision Exp is a model from DeepSeek. 8 benchmarks count toward its index, in 6 categories.
IndexAll categories, out of 100.60.4±7.2Median 51.0
CoverageIndex weight that has results.85%
SpeedOutput tokens per second.74/sMedian 67/s
First tokenSeconds to the first output token.3.1 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.44batch $0.11Median $0.60
Output / 1MUS dollars per 1M output tokens.$1.32batch $0.33 Batch price per 1M output tokens.Median $2.55
ContextMaximum tokens in one request.1.05MMedian 262K
EloLMArena rating and rank.—Median 1422
Details
From OpenRouter- API IDThe model ID on OpenRouter.
deepseek/deepseek-v4-flash-vision-exp- Max outputMaximum output tokens per request.
- 944K
- Knowledge cutoffLast date of training data.
- —
- ToolsTool calls on OpenRouter.
- Yes
- JSON outputOutput follows a given JSON schema.
- Yes
- Cache read / 1MUS dollars per 1M cached tokens.
- $0.014
- WeightsLink to the published weights.
- Hugging Face (opens in a new tab) ↗
- RetiresDate OpenRouter removes the model.
- —
Where to run
APIs that serve this model.ProviderTypeMaker, cloud, host or router.InputOutputContext
US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).
Run locally
304.65B parameters- 16-bit
- 640.8 GB
- 8-bit
- 340.9 GB
- 4-bit
- 194.9 GB
Memory need with a short context. The 4-bit copy needs more than 128 GB. Compare local models
Capabilities
Index per category, out of 100.Results
8 countedBenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Sources
BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseLiveBenchNo licence statedmodels.devMITHistory
5 releases23 Oct 202612 Nov 2026
23 Oct 202612 Nov 2026
Questions
- How much does DeepSeek V4 Flash Vision Exp cost?
- $0.44 per 1M input tokens, $1.32 per 1M output tokens.
- How good is DeepSeek V4 Flash Vision Exp?
- Its index is 60.4 out of 100. That is place 71 of 283 ranked models.
- What is DeepSeek V4 Flash Vision Exp best at?
- Agentic: 71.8 out of 100, place 18 of 218.
- How fast is DeepSeek V4 Flash Vision Exp?
- 74 output tokens per second, 3.1 s to the first token.
- What is the context window of DeepSeek V4 Flash Vision Exp?
- 1.05M tokens.
- Is DeepSeek V4 Flash Vision Exp open source?
- Yes. Its weights are published.
- When was DeepSeek V4 Flash Vision Exp released?
- August 2026.
Badge
- HTML
<a href="https://inference360.ai/models/deepseek-deepseek-v4-flash-vision-exp"><img src="https://inference360.ai/badges/deepseek-deepseek-v4-flash-vision-exp.svg" alt="DeepSeek V4 Flash Vision Exp on Inference360: place 71 of 283, index 60.4" height="20"></a>- Markdown
[](https://inference360.ai/models/deepseek-deepseek-v4-flash-vision-exp)