OpenRouter 模型 ↗ · 2026-08-21
deepseek/deepseek-v4-flash-vision-exp
Model release OpenRouter 模型 Source language: Chinese
OpenRouter 于 2026-08-21 收录该模型(收录时间不等于模型正式发布日期);上下文:1,048,576 tokens;输入价:$0.4400/百万 tokens;输出价:$1.3200/百万 tokens;定位(来源描述):DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash…
Full text
DeepSeek: DeepSeek V4 Flash Vision Exp
deepseek/deepseek-v4-flash-vision-exp
Model weights
Compare
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731Opens in new tab from DeepSeek, adding image understanding while matching the base model on text capabilities including agents, reasoning, and world knowledge. It is a sparse mixture-of-experts model with 13B active parameters out of 284B total.
It is suited for document and chart understanding, visual question answering, and multimodal agent workflows that interleave text and images.
Modalities
In / out price
51% off
$0.2156 / $0.6468per 1M
Context
1.0M
Released
Aug 21, 2026
Compare
Providers
Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).
Latency / throughput
$0.4400$1.3200$0.0140003.78s70 tok/s
99.97%
51% off
$0.44$0.2156$1.32$0.6468$0.014$0.0068601.10s66 tok/s
99.46%
Priority51% off
$0.66$0.3234$1.98$0.9702$0.021$0.0102900.88s106 tok/s
98.37%
Not used in Standard routing:Why these endpoints are not used
Flex51% off
$0.352$0.1725$1.056$0.5174$0.0112$0.0054881.38s105 tok/s
50.00%
ProviderInput / Output /M
Input $0.44 / Output $1.32
70 tok/s99.97% uptime
Input $0.2156 / Output $0.6468
51% off
66 tok/s99.46% uptime
Input $0.3234 / Output $0.9702
Priority
+11 more label
106 tok/s98.37% uptime
Not used in Standard routing:Why these endpoints are not used
Input $0.1725 / Output $0.5174
Flex
+11 more label
105 tok/s50.00% uptime
Pricing
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Weighted average
Input
$0.04916/M tokens
Output
$1.147/M tokens
DeepSeek V4 Flash Vision Exp — Price history
Price history
No effective price data for this selection
Priority
$0.0418$0.97089.9%5.9%
$0.0474$0.64680.6%9.3%
$0.0499$1.32091.6%84.8%
Not used in Standard routing:Why these endpoints are not used
Flex
$0.0380$0.51780.5%0.0%
ProviderInput / Output /M
Token share
Effective in $0.0418 / Effective out $0.970
PriorityToken share
5.9%
Effective in $0.0474 / Effective out $0.646
Token share
9.3%
Effective in $0.0499 / Effective out $1.320
Token share
84.8%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.0380 / Effective out $0.517
FlexToken share
0.0%
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Throughput
106tok/s
P50, best across providers
Latency
0.88s
P50, best provider
Reasoning effortLatency / throughput
AutoExacto benchmarks
GPQA DiamondTAU-BenchGMICloud90.4%74.4%
Uptime
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.92%
Availability over the last 3 days
Last 72 hours
Availability 99.92%
3 Days Ago2 Days AgoYesterdayNow
Availability over the last 24 hours
OpenRouter Availability
99.91%
Without Routing
97.77%
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
Benchmarks
Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.
Benchmark score summary for DeepSeek: DeepSeek V4 Flash Vision Exp (Artificial Analysis)
SourceBenchmarkScore
Artificial AnalysisDeepSeek V4 Flash Vision (Max) Coding Index65.0
Artificial AnalysisDeepSeek V4 Flash Vision (Max) Agentic Index47.5
Artificial AnalysisDeepSeek V4 Flash Vision (Max) GPQA Diamond91.3%
Artificial AnalysisDeepSeek V4 Flash Vision (Max) HLE34.5%
Artificial AnalysisDeepSeek V4 Flash Vision (Max) AA-LCR81.3%
Artificial AnalysisDeepSeek V4 Flash Vision (Max) τ-Bench Banking41.0%
Artificial AnalysisDeepSeek V4 Flash Vision (Max) GDPval-AA52.7%
Artificial AnalysisDeepSeek V4 Flash Vision (Max) CritPt10.9%
Artificial AnalysisDeepSeek V4 Flash Vision (Max) SciCode49.7%
Artificial AnalysisDeepSeek V4 Flash Vision (Max) Terminal-Bench 4.012.1%
Artificial AnalysisDeepSeek V4 Flash Vision (Max) Terminal-Bench 2.174.2%
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
1.
Kilo Code
Kilo Code is an open-source AI coding agent that works across VS Code, JetBrains, and CLI to help developers ship code faster with agentic workflows.
23.9Btokens
2.
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
20.5Btokens
3.
DeepSeek Harness
new
9.81Btokens
4.
pi
There are many coding agents, but this one is yours.
5.52Btokens
5.
Nous Research API
Nous Research is an AI research team focused on advancing open-source AI.
2.48Btokens
Rest of OpenRouter
5.15B
Top 5 Apps
905M
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Not currently available through EU in-region routing. In-region routing docs
Documentation
Guides, cookbooks, blog posts, and tools for building with DeepSeek: DeepSeek V4 Flash Vision Exp on OpenRouter.
Does DeepSeek V4 Have Vision?Blog post
Why Use OpenRouter for DeepSeekBlog post
DeepSeek V4 Is Earning Agentic Token ShareBlog post
Frequently asked questions
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, reasoning, and world knowledge. It is a sparse mixture-of-experts model with 13B active parameters out of 284B total.
The DeepSeek V4 Flash Vision Exp documentation on OpenRouter includes the Does DeepSeek V4 Have Vision? blog post, the Why Use OpenRouter for DeepSeek blog post, and the DeepSeek V4 Is Earning Agentic Token Share blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.
DeepSeek V4 Flash Vision Exp costs $0.2156/M input tokens and $0.6468/M output tokens, with separate rates for Cache Read at $0.00686/M tokens.
DeepSeek V4 Flash Vision Exp has a 1,048,576 token context window. It supports up to 262,144 completion tokens.
Yes. DeepSeek V4 Flash Vision Exp accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
DeepSeek V4 Flash Vision Exp accepts text and images as input and returns text.
DeepSeek V4 Flash Vision Exp is served by 2 providers on OpenRouter: DeepInfra and GMICloud. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
DeepSeek V4 Flash Vision Exp was released on August 21, 2026.