DeepSeek

DeepSeek-V3.2

DeepSeek-V3.2 with sparse attention for efficient long-context inference, offering hybrid thinking at a low price across gateways.

ActiveAvailable from 17 providers
Tool callingCan invoke external tools and APIs (function calling) mid-response.Structured outputCan return JSON or schema-constrained responses instead of free text.ReasoningUses extended thinking / chain-of-thought for harder multi-step problems.Effort controlLets you dial thinking depth (low / medium / high) to trade cost for quality.Fine-tuningSupports training a custom variant on your own data.

Source: DeepSeek API models, DeepSeek models

Price per 1M tokens via StreamLake (OpenRouter)
$0.2288 in / $0.3432 out
Context window131,072
Max output65,536
Cache read$0.02288 / M
ModalitiesText → Text
Priced across17 providers

Pricing

Every billing leg from the live catalog, in USD per 1M tokens.

Billing legRate
Input$0.2288 / M
Output$0.3432 / M
Cache read$0.02288 / M

Cost calculator

Billing-grade math over the rate card above, including the thinking tokens most estimates miss.

Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.

Estimated monthly cost
$66.35
at current list prices
Fresh input$45.76
Cached input$0.00
Output incl. thinking$20.59
Track this automatically →

Compare providers

The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.

PlatformInput / MOutput / MCache read / MBatchAccess
StreamLakeLowest
$0.2288$0.3432$0.02288—via OpenRouter
Baidu
$0.252$0.378$0.0252—via OpenRouter
AtlasCloud
$0.26$0.38$0.13—via OpenRouter
DeepInfra
$0.26$0.38$0.13—via OpenRouter
Novita
$0.269$0.4$0.1345—via OpenRouter
SiliconFlow
$0.259$0.42$0.135—via OpenRouter
GMICloud
$0.29$0.43$0.03—via OpenRouter
Venice
$0.33$0.48$0.16—via OpenRouter
Alibaba
$0.3705$1.11$0.0741—via OpenRouter
DigitalOcean
$0.425$1.36$0.15—via OpenRouter
Friendli
$0.5$1.5$0.25—via OpenRouter
Phala
$1$1$0.5—via OpenRouter
Google
$0.56$1.68——via OpenRouter
Azure AI Foundry
$0.58$1.68——Direct
Azure AI Foundry (Fireworks)
$0.62$1.85——Direct
Azure AI Foundry · Data zone
$0.64$1.85——Direct
SambaNova
$3$4.5——via OpenRouter

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $0.2288 / $0.3432 per 1M since July 10, 2026.

More from DeepSeek

Other models from the same provider.

DeepSeek-V4 Pro
deepseek/deepseek-v4-pro
$1.74 / $3.48 in / out per 1M
DeepSeek-V4 Flash
deepseek/deepseek-v4-flash
$0.14 / $0.28 in / out per 1M
DeepSeek-V3.1
deepseek/deepseek-v3.1
$0.21 / $0.79 in / out per 1M
DeepSeek-V3
deepseek/deepseek-v3
$0.2002 / $0.8001 in / out per 1M
DeepSeek-R1
deepseek/deepseek-r1
$0.5 / $2.15 in / out per 1M

Stop estimating. Track it.

SuperPenguin meters every DeepSeek-V3.2 call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.

Get started free

Rates are generated from SuperPenguin's live pricing catalog.