Enterprise DNAEnterprise DNA
DeepSeek logo

Models · Best coding

DeepSeek V4 Flash Vision Exp

by DeepSeek

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding imag.

Visit DeepSeek ↗

Our verdict

Not reviewed yet

We have not reviewed DeepSeek V4 Flash Vision Exp yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About DeepSeek V4 Flash Vision Exp

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.

Notes

DeepSeek V4 Flash Vision Exp is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$0.440 per million tokens
Checked OpenRouter models API
Output price
$1.32 per million tokens
Checked OpenRouter models API
Price on deepinfra
$0.0069 per million cached input tokens
Checked OpenRouter models API
Price on deepinfra
$0.216 per million input tokens
Checked OpenRouter models API
Price on deepinfra
$0.647 per million output tokens
Checked OpenRouter models API
Price on gmicloud
$0.014 per million cached input tokens
Checked OpenRouter models API
Price on gmicloud
$0.440 per million input tokens
Checked OpenRouter models API
Price on gmicloud
$1.32 per million output tokens
Checked OpenRouter models API
Price on siliconflow
$0.028 per million cached input tokens
Checked OpenRouter models API
Price on siliconflow
$0.440 per million input tokens
Checked OpenRouter models API
Price on siliconflow
$1.32 per million output tokens
Checked OpenRouter models API
Latest preview version
deepseek/deepseek-v4-flash-vision-exp-20260821
Checked OpenRouter models API

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `deepseek/deepseek-v4-flash-vision-exp`.

  • openrouter · deepseek/deepseek-v4-flash-vision-exp · Docs

OpenRouter id: deepseek/deepseek-v4-flash-vision-exp

Price

What DeepSeek V4 Flash Vision Exp costs, over time

Input price

$0.220 to $0.440

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$0.660 to $1.32

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
deepinfraCached input$0.0069 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraInput$0.216 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$0.647 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudCached input$0.014 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudInput$0.440 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudOutput$1.32 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowCached input$0.028 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowInput$0.440 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowOutput$1.32 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much DeepSeek V4 Flash Vision Exp is used

Tokens served a day

27.2B to 17.5B

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How DeepSeek V4 Flash Vision Exp scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index34.8indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index65indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index47.5indexAs of 10 Nov 2026Artificial Analysis via OpenRouter

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    output per mtok: 0.6468 to 1.32

    Source: OpenRouter models API

  2. Price changed

    input per mtok: 0.2156 to 0.44

    Source: OpenRouter models API

  3. Price changed

    output per mtok: 0.66 to 0.6468

    Source: OpenRouter models API

  4. Price changed

    input per mtok: 0.22 to 0.2156

    Source: OpenRouter models API

  5. Price changed

    output per mtok: 0.6468 to 0.66

    Source: OpenRouter models API

  6. Price changed

    input per mtok: 0.2156 to 0.22

    Source: OpenRouter models API

  7. Price changed

    output per mtok: 0.66 to 0.6468

    Source: OpenRouter models API

  8. Price changed

    input per mtok: 0.22 to 0.2156

    Source: OpenRouter models API

USAGE / OPENROUTER

How much DeepSeek V4 Flash Vision Exp is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
74.6B ▲17.4%
Requests, last 7 days
1.3M
Tool calls, last 7 days
491K
Average cost per request
30.8¢
Price per million tokens
$0.44 in · $1.32 out
025B50B19 Sept: 27.2B tokens, 1.2M requests20 Sept: 26.2B tokens, 1M requests21 Sept: 26.3B tokens, 704K requests22 Sept: 30.1B tokens, 1.4M requests23 Sept: 27B tokens, 955K requests24 Sept: 25.8B tokens, 993K requests25 Sept: 15.6B tokens, 532K requests26 Sept: 12.2B tokens, 402K requests27 Sept: 25B tokens, 621K requests28 Sept: 19.5B tokens, 584K requests29 Sept: 13.3B tokens, 345K requests30 Sept: 11.1B tokens, 275K requests1 Oct: 12.3B tokens, 281K requests2 Oct: 11.2B tokens, 281K requests3 Oct: 10.6B tokens, 269K requests4 Oct: 9.6B tokens, 254K requests5 Oct: 11.3B tokens, 259K requests6 Oct: 12.9B tokens, 288K requests7 Oct: 13.9B tokens, 304K requests8 Oct: 14.3B tokens, 323K requests9 Oct: 15.6B tokens, 381K requests10 Oct: 12.6B tokens, 341K requests11 Oct: 10B tokens, 307K requests12 Oct: 13.3B tokens, 304K requests13 Oct: 13.6B tokens, 320K requests14 Oct: 15.5B tokens, 312K requests15 Oct: 13.9B tokens, 323K requests16 Oct: 13.5B tokens, 326K requests17 Oct: 7.4B tokens, 279K requests18 Oct: 9.5B tokens, 293K requests19 Oct: 10.3B tokens, 344K requests20 Oct: 9.4B tokens, 375K requests21 Oct: 8.6B tokens, 266K requests22 Oct: 10B tokens, 244K requests23 Oct: 9B tokens, 204K requests24 Oct: 5.9B tokens, 175K requests25 Oct: 10.1B tokens, 171K requests26 Oct: 13B tokens, 222K requests27 Oct: 18.3B tokens, 340K requests28 Oct: 17.1B tokens, 330K requests29 Oct: 8.1B tokens, 182K requests30 Oct: 7.2B tokens, 154K requests31 Oct: 5.5B tokens, 130K requests1 Nov: 5.7B tokens, 146K requests2 Nov: 9.1B tokens, 178K requests3 Nov: 10.9B tokens, 189K requests4 Nov: 10.1B tokens, 205K requests5 Nov: 7B tokens, 161K requests6 Nov: 8.6B tokens, 166K requests7 Nov: 8.8B tokens, 206K requests8 Nov: 14.6B tokens, 216K requests9 Nov: 8.1B tokens, 143K requests10 Nov: 17.5B tokens, 242K requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with DeepSeek V4 Flash Vision Exp.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-06. Hosting routes and app features can differ.

DeveloperDeepSeek
Exact model identifierdeepseek/deepseek-v4-flash-vision-exp
Inputtext, image
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
MIT, open weights
Context length
1M tokens
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
21 Aug 2026
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

deepseek/deepseek-v4-flash-vision-exp: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-06
openrouter.ai ↗

Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.

Checked 2026-11-06
Licence source ↗

Licence declared in the deepseek-ai/DeepSeek-V4-Flash-Vision-Exp model repository on Hugging Face, which holds the weights files. Read the licence terms before use.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Build an appWorkflow & starter prompt ↗Extract document dataWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Coding Index: 65 (2026-11-09) ↗Agentic Index: 47.5 (2026-11-09) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →