WhichAI / Models / DeepSeek V4 Flash Vision Exp

DeepSeek V4 Flash Vision Exp

· verified October 13, 2026

public paid api open-weights reasoning agents vision long-context value local

Provider

Statuspublic

AA Intelligence Index34.8 (official, read October 13, 2026)

Released2026-08-21

Context window1.05M

ModalitiesText + image

API price $/1M (in / out)$0.216 / $0.647 (OpenRouter)

Speedn/a

AccessAPI $0.216/$0.647 per 1M tokens on OpenRouter · open weights · listed August 21, 2026

In one line

DeepSeek V4 Flash Vision Exp by DeepSeek, measured by Artificial Analysis at 34.8 on the Intelligence Index, 65 on coding and 47.5 on agentic work. Added to WhichAI automatically from live data on October 13, 2026: no editorial review yet, so judge it by the numbers, not by a verdict. OpenRouter's description: “DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding...”

Alternatives worth a look

DeepSeek V4 Flash 0731 (DeepSeek) · AA 34.3API $0.016/$0.64 per 1M tokens on OpenRouter · open weights · listed July 31, 2026
Gemini 3.6 Flash (Google) · AA 34Free tier in AI Studio and the Gemini app (rate-limited) · API $1.50/$7.50 per 1M tokens
Muse Spark 1.1 (Meta) · AA 33.7API via Meta Superintelligence Labs (Meta's first paid model, July 9, 2026)

Open DeepSeek's official app ↗ Open in the WhichAI app Not sure? Take the 30-second finder

Artificial Analysis Intelligence Index, official scale (the number published on artificialanalysis.ai), relayed by OpenRouter and refreshed automatically: last read October 13, 2026. 210 models carry a current official measurement. A value marked ~ is converted from an earlier snapshot because no current measurement is published; an unmeasured model is never ranked. Context, price, modality and listing dates come from the public OpenRouter model list (refreshed automatically on the live site; static copy retrieved October 3, 2026) and vendor pages. Missing values are not published or not yet verified - shown as -. Sources are linked inside the app (the Ranking chapter and About > Methodology).