DeepSeek

DeepSeek-V3.1

DeepSeek-V3.1, the hybrid thinking model that unified chat and reasoning, available in a stable Terminus snapshot.

ActiveAvailable from 11 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 DeepInfra (OpenRouter)
$0.21 in / $0.79 out
Context window131,072
Max output65,536
Cache read$0.13 / M
ModalitiesText → Text
Priced across11 providers

Pricing

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

Billing legRate
Input$0.21 / M
Output$0.79 / M
Cache read$0.13 / 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
$89.40
at current list prices
Fresh input$42.00
Cached input$0.00
Output incl. thinking$47.40
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
DeepInfraLowest
$0.21$0.79$0.13—via OpenRouter
AtlasCloud
$0.3$0.95$0.13—via OpenRouter
Novita
$0.27$1$0.135—via OpenRouter
SiliconFlow
$0.27$1——via OpenRouter
StreamLake
$0.3426$1.03——via OpenRouter
SambaNova
$0.65$1.5——via OpenRouter
Wandb
$0.55$1.65$0.55—via OpenRouter
Google
$0.6$1.7——via OpenRouter
Mara
$0.6$1.7——via OpenRouter
Azure AI Foundry
$1.23$4.94——Direct
Azure AI Foundry · Data zone
$1.36$5.43——Direct

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $0.21 / $0.79 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-V3.2
deepseek/deepseek-v3.2
$0.2288 / $0.3432 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-V3.1 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.