DeepSeek V3.1

DeepSeek · Mid

Compare →

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Input / 1M

$0.21

Output / 1M

$0.79

Cached input / 1M

$0.13

Context window

163K

Where it sits

93rd-cheapest mid model

by blended $/Mtok among 262 listed mid models

38% below the mid median

blended $/Mtok across 262 mid models

Output costs 3.8× input

$0.21 in / $0.79 out per 1M

Cached input saves 38%

$0.13 vs $0.21 per 1M fresh

Held flat since launch (Jun 2026)

no blended price change recorded

Computed live from current prices and this model's history — not hand-written, so it stays accurate as prices move.

Price history

Only one price on record so far — the history chart appears once a price changes.

Snapshots

Effective Input Output Cached in Note Source
11 Jun 2026 $0.21 $0.79 $0.13 Imported from OpenRouter openrouter.ai

More from DeepSeek