Context
1M
Max output
393K
Serving providers
1
Cheapest input
$2.40 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Empiriolabs Cheapest | $2.40 | $4.80 | 1 | ||||||||||
Standardempiriolabs/deepseek-v4-pro:variant3
| |||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Price history is accruing. We record a point each day a listed seller price changes; the full backfill lands shortly.
Cost calculator
estimate your monthly spend on this model$864
estimated / month
Model IDs
copy the exact identifier for your platformempiriolabs/deepseek-v4-pro:variant3
Frequently asked questions
DeepSeek V4 Pro Variant3 pricing, context and availabilityHow much does DeepSeek V4 Pro Variant3 cost?
DeepSeek V4 Pro Variant3 costs $2.40 per 1M input tokens from Empiriolabs, and $4.80 per 1M output tokens from Empiriolabs.
What is the context window of DeepSeek V4 Pro Variant3?
DeepSeek V4 Pro Variant3 accepts up to 1M tokens of context and can return up to 393K output tokens.
What can DeepSeek V4 Pro Variant3 do?
DeepSeek V4 Pro Variant3 supports reasoning and structured output.
Other DeepSeek models
compare pricing across the DeepSeek lineupDeepSeek V4 Flash 0423$0.09/1M · 24 providersDeepSeek V4.1 Flash$0.01/1M · 22 providersDeepSeek V4 Pro 0423$0.528/1M · 22 providersDeepSeek V4 Flash 0731$0.059/1M · 21 providersDeepSeek R1$0.40/1M · 17 providersDeepSeek V4 Pro 0813$0.107/1M · 16 providersDeepSeek V4.1 Flash 1017$0.14/1M · 13 providersDeepSeek V3$0.19/1M · 13 providers
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Nov 5, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI