Skip to content

DeepSeek · Chat

DeepSeek V4 Flash Vision Exp

DeepSeek 🇨🇳ChatDeepSeek familyOpen weights. One of its sources says the weights are publicly available.The maker lists this model as deprecated (25 Sep 2026).
From Netmind's listing:
DeepSeek-V4-Flash-Vision-Exp is an experimental multimodal variant of DeepSeek-V4-Flash, adding image understanding to the fast, cost-effective 1M-context reasoning model with thinking mode and tool calls.
llminfo IQ
136.6
Maker's price
$0.525 blended / 1M
Max context
1.1M
Listings
41

Evidence and sources

🤗 deepseek-ai/DeepSeek-V4-Flash-Vision-Expllminfo IQ 136.6, ranked among chat models. From 32 benchmarks. A fair amount of data behind it.How llminfo IQ is computedCoding IQ 109.6, 95% interval 90–129. From 4 benchmark families across 2 sources. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedGood value (63.0). Cheaper per task than its benchmark results predict. From 2 benchmarks with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 21 Aug 2026Maker HQ: CN (according to DeepSeek's own website)
All rankings: #107 on OpenRouter today #116 on OpenRouter this month #120 on OpenRouter this week #139 on NanoGPT recentlySources: DeepInfra data, LiteLLM data, Models.dev data, AI/ML API data, NetMind.AI, llminfo researchPrimary data from DeepInfra from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode from NetMind.AI: description from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 3 of the 9 peers that say either way have open weights.

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (25 Sep 2026).

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 10 maker's prices.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingWeb search

Listings

 DeepSeekdeepseek-v4-flash-vision-expSources: LiteLLM data, Models.dev data1M$0.30cache read $0.006$1.20——
 LlmgatewayInference by DeepSeekdeepseek-v4-flash-vision-expSource: LLMGateway dataNot published by the provider$0.14cache read $0.0028$0.28——
 Eden AIInference by DeepSeekdeepseek/deepseek-v4-flash-vision-expSource: Models.dev data1M$0.15cache read $0.003$0.60——
 Commandcodedeepseek/deepseek-v4-flash-vision-expSource: Models.dev data1M$0.15cache read $0.003$0.60——
 Aihubmixdeepseek-v4-flash-vision-expSource: AIHubMix data docs1M$0.155cache read $0.0031$0.62——
 OpenRouterInference by DeepInfradeepseek/deepseek-v4-flash-vision-exp · fp8/flex · fp8Source: OpenRouter data docs1M$0.1725cache read $0.0055$0.51741412,177.5ms
 Fastrouterdeepseek/deepseek-v4-flash-vision-expSource: FastRouter data1M$0.2156cache read $0.0069$0.6468——
 Hugging FaceInference by DeepInfradeepseek-ai/DeepSeek-V4-Flash-Vision-ExpSource: Hugging Face Inference Providers data1M$0.2156$0.6468——
 Kilodeepseek/deepseek-v4-flash-vision-expSources: Kilo AI Gateway data, Models.dev data1M$0.2156cache read $0.0069$0.6468——
 NanoGPTdeepseek/deepseek-v4-flash-vision-expSources: Models.dev data, NanoGPT1M$0.2156cache read $0.0069$0.6468——
Show all 35 listings

Showing 10 of 35: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Aimlapi, DeepInfra, Evolink, Fireworks AI, Flowdot, Gmicloud, Llmgateway Providers, Netmind, Nous Portal, Novita AI, Orcarouter, Ppio, SiliconFlow, Vercel, Wavespeed.

6 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

General

Agentic

Source: OpenRouter benchmark exports
21 Aug 2026 version · 90-day results
Across 6 providers lowest 67.8% median 75% highest 76.7%OpenRouter's automatic routing 74.8%
Show results from 6 providers and OpenRouter's automatic routingHide results from 6 providers and OpenRouter's automatic routing
  • Novita
  • DeepInfra
  • SiliconFlow
  • OpenRouter's automatic routing
  • GMICloud
  • AtlasCloud
  • Fireworks

Science

GPQA Diamond7 results
Source: OpenRouter benchmark exports
21 Aug 2026 version · 90-day results
Across 6 providers lowest 83.4% median 89% highest 90.9%OpenRouter's automatic routing 88%
Show results from 6 providers and OpenRouter's automatic routingHide results from 6 providers and OpenRouter's automatic routing
  • GMICloud
  • Novita
  • SiliconFlow
  • DeepInfra
  • OpenRouter's automatic routing
  • Fireworks
  • AtlasCloud

Coding

DeepSWESource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
NL2RepoSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Reasoning

ZEROBenchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Math

Data credits: Data by LLM Stats · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark

Also known as: deepinfra/deepseek-v4-flash-vision-exp, deepseek-ai/deepseek-v4-flash-vision-exp, deepseek/deepseek-v4-flash-vision-exp, fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp, fireworks_ai/deepseek-v4-flash-vision-exp, gmi/deepseek-ai/deepseek-v4-flash-vision-exp, novita/deepseek/deepseek-v4-flash-vision-exp

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works