DeepSeek V3 by DeepSeek

Model family · Model APIs & inference · indexed, not reviewed

on OpenRouter

Not reviewed

No score, grade or rank. This listing is facts from OpenRouter and our own checks, and it stays out of the rankings until the panel reviews it.

How the index works

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
What OpenRouter says about DeepSeek V3.2

Facts

Maker: DeepSeek
Models: 5 on OpenRouter
Newest: deepseek/deepseek-v3.2

From OpenRouter and our own checks. JSON · Markdown

Why it's listed

OpenRouter lists it, with prices from the providers that serve it.

Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.

Models 5

Model	Released	Context	Input / 1M	Output / 1M	Supports
DeepSeek V3.2 `deepseek/deepseek-v3.2`	Dec 2025	163k	$0.28	$0.42	tools, structured output, reasoning, caching
DeepSeek V3.2 Exp `deepseek/deepseek-v3.2-exp`	Sep 2025	163k	$0.27	$0.41	tools, structured output, reasoning
DeepSeek V3.1 `deepseek/deepseek-chat-v3.1`	Aug 2025	163k	$0.25	$0.95	tools, structured output, reasoning, caching
DeepSeek V3 0324 `deepseek/deepseek-chat-v3-0324`	Mar 2025	163k	$0.25	$1	tools, structured output
DeepSeek V3 `deepseek/deepseek-chat`	Dec 2024	163k	$0.2574	$1.0287	tools, structured output

Prices and limits as OpenRouter lists them, in dollars per million tokens; a provider's own price can differ.

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.