Skip to content

DeepSeek V3.2

DeepSeek · Open weights · 164K context · released Dec 1, 2025 · checked 7h ago

Ways to buy 14

Way to buyIn / out per 1M
GMICloud
fp8 · cached $0.022
$0.209 / $0.31Cheapest
AtlasCloud
fp8 · cached $0.13
$0.26 / $0.38+24% vs cheapest
DeepInfra
fp4 · cached $0.13
$0.26 / $0.38+24% vs cheapest
Venice
Default region · cached $0.13
$0.268 / $0.39+28% vs cheapest
SiliconFlow
fp8 · cached $0.135
$0.259 / $0.42+28% vs cheapest
Novita AI
fp8 · cached $0.135
$0.269 / $0.4+29% vs cheapest
Baidu
fp8 · cached $0.028
$0.28 / $0.42+35% vs cheapest
DigitalOcean
Default region · cached $0.09
$0.3 / $0.96+99% vs cheapest
Qwen (Alibaba)
fp8 · cached $0.074
$0.371 / $1.11+137% vs cheapest
Friendli
Default region · cached $0.25
$0.5 / $1.5+221% vs cheapest
Google Vertex AI
Default region
$0.56 / $1.68+259% vs cheapest
Phala
Default region · cached $0.5
$1 / $1+327% vs cheapest
Mara
Default region
$3 / $4.5+1342% vs cheapest
SambaNova
Default region
$3 / $4.5+1342% vs cheapest

USD per 1M tokens. Regions are separate routes.

Through a gateway

Your own numbers

100M input and 20M output tokens a month: $27.07 direct.

No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.

Related models

In / out per 1M
DeepSeek V4.1 Flash
DeepSeek · 1MCheapest: $0.131 on Morph
$0.15 / $0.6
DeepSeek V4 Flash Vision Exp
DeepSeek · 1M
$0.216 / $0.647
DeepSeek V4 Pro 0813
DeepSeek · 1MCheapest: $0.525 on Baidu (fp8)
$0.66 / $1.98
DeepSeek V4 Flash 0731
DeepSeek · 1.31M
$0.053 / $0.158
GPT-6 Luna
OpenAI · 1.05MCheapest: $0.1 on OpenAI (flex)
$0.1 / $0.5
GPT-6 Luna Pro
OpenAI · 1.05MCheapest: $0.1 on OpenAI (flex)
$0.1 / $0.5
Qwen3.8 Omni Flash
Qwen (Alibaba) · 1M
$0.15 / $0.47
Muse Spark 1.3 Contributor
Meta · 1M
$0.1 / $0.2

About DeepSeek V3.2

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.

Takes text in and returns text. First listed Sep 23, 2026. Up to 66K output tokens. Blended price $0.234 per 1M tokens at 3 input to 1 output. Model id deepseek-v3-2.

Price history

No list-price history: this model is sold by hosts rather than its lab.

Across fru.devCompany profile

Questions

How much does DeepSeek V3.2 cost?

$0.209 per million input tokens and $0.31 per million output tokens, with cached input at $0.022.

What is the context window of DeepSeek V3.2?

164K tokens, with up to 66K tokens of output.

Where is DeepSeek V3.2 cheapest?

Of 14 routes tracked, GMICloud is cheapest at $0.209 input and $0.31 output per million tokens.

Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Price changes by email

Thursdays, only in weeks when an LLM API list price changed.

Double opt-in. Unsubscribe any time.