DeepSeek

DeepSeek-R1

DeepSeek-R1, the open-weight reasoning model that popularized transparent chain-of-thought, available across inference gateways.

ActiveReleased May 28, 2025Available 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 (vendor fine-tune API or self-hosted open weights).

Source: DeepSeek API models, DeepSeek models, Field resolution verification

Price per 1M tokens via DeepInfra (OpenRouter)
$0.5 in / $2.15 out
Context window131,072
Max output65,536
Cache read$0.35 / M
Input
  • Text
Output
  • Text
Priced across11 providers

Pricing

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

Billing legRate
Input$0.5 / M
Output$2.15 / M
Cache read$0.35 / 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
$229
at current list prices
Fresh input$100
Cached input$0.00
Output incl. thinking$129
Track this automatically →

Compare providers

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

PlatformRegionInput / MOutput / MCache read / MBatchAccess
DeepInfraLowest
-$0.5$2.15$0.35-via OpenRouter
SiliconFlow
-$0.5$2.18--via OpenRouter
StreamLake
-$0.571$2.29--via OpenRouter
Novita
-$0.7$2.5$0.35-via OpenRouter
Azure AI Foundry
-$1.35$5.4--Direct
AWS Bedrock
$1.35$5.4--Direct
Azure AI Foundry · Data zone
-$1.49$5.94--Direct
Azure OpenAI
-$1.49$5.94--via OpenRouter
Azure AI Foundry · Regional
$1.49$5.94--Direct
Together AI
-$3$7--Direct
Fireworks AI
-$3$8--Direct

Some hosts price by region. Shown rates match the selected region.

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $0.5 / $2.15 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
$0.269 / $0.4 in / out per 1M
DeepSeek-V3.1
deepseek/deepseek-v3.1
$0.25 / $0.95 in / out per 1M
DeepSeek-V3
deepseek/deepseek-v3
$0.2574 / $1.03 in / out per 1M

Stop estimating. Track it.

SuperPenguin meters every DeepSeek-R1 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.