WhichAI / Models / DeepSeek V3.1

DeepSeek V3.1

· verified October 13, 2026

legacy paid api open-weights local

Provider

Statuslegacy

AA Intelligence Index13.7 (official, read October 13, 2026)

Released2025-08-21

Context window164K

ModalitiesText

API price $/1M (in / out)$0.25 / $0.95 (OpenRouter)

Speedn/a

AccessAPI $0.25/$0.95 per 1M tokens on OpenRouter · open weights · listed August 21, 2025

In one line

DeepSeek V3.1 by DeepSeek, measured by Artificial Analysis at 13.7 on the Intelligence Index. 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-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.”

Alternatives worth a look

Mercury 2 (Inception Labs) · AA 13.8API
Nova 2 Lite (Amazon) · AA 13.4API $0.3/$2.5 per 1M tokens on OpenRouter · listed December 2, 2025
Qwen3.5-9B (Alibaba) · AA 13.3API $0.1/$0.15 per 1M tokens on OpenRouter · open weights · listed March 10, 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).