Model Price Index
Updated 2026-07-14 · Changelog

DeepSeek-V4 Pro

DeepSeek

DeepSeek's higher-tier V4 model with thinking mode and configurable reasoning effort for complex reasoning and coding

$0.435

Input

$0.87

Output

per 1M tokens

Ratesper 1M tokens

Input$0.435
Output$0.87
Cache Read$0.0036

Estimate Your Monthly Cost

A request with input and output tokens, requests / month at a % cache hit rate $39.15/mo

Compare all models at this workload →

Excludes cache writes and batch discounts.

Also routable via OpenRouter at the same list price. OpenRouter adds a 5.5% platform fee on pay-as-you-go credits (verified 2026-07-08).

Same Model, Other Providersper 1M tokens

Provider comparison for DeepSeek-V4 Pro
ProviderInput / 1MOutput / 1MCache Read / 1MCache Write / 1Mvs This Page
DeepSeekThis page$0.435$0.87$0.0036
Together AI$1.74$3.48$0.20+300%

Specifications

API Model IDdeepseek-v4-pro
Context Window1M tokens
Max Output384K tokens
Modalitiestext
Capabilitiestool-use · streaming · json-mode · code · reasoning

More DeepSeek Text / Chat Models

DeepSeek-V4 Flash · DeepSeek-V3.2 Chat · DeepSeek-V3.2 Reasoner