Polarison

DeepSeek

DeepSeek V4 Pro pricing and benchmarks

DeepSeek’s larger V4 model with thinking and non-thinking modes and tool calls.

Input
$1.32
per 1M tokens
Cached input
$0.044
per 1M tokens
Output
$3.96
per 1M tokens
Capability index
155.5
#10 of 16 tracked

How capable is DeepSeek V4 Pro?

DeepSeek V4 Pro scores 155.5 on the Epoch Capabilities Index (confidence interval 153.8157.8), ranking #10 of the 16 rated models we track.

BenchmarkTestsScore
GPQA DiamondScience reasoning
88.9%
FrontierMath (Tiers 1–3)Advanced math
64.6%
SimpleQA VerifiedFactual accuracy
52.9%
ARC-AGI-2Abstract reasoning
61.3%
DeepSWECoding
APEX-AgentsAgentic work

Source: Epoch AI (as “DeepSeek V4 Pro 0813”), best recorded result, CC BY 4.0. A dash means no published score. Compare all models

What DeepSeek V4 Pro costs in practice

WorkloadMonthly cost
Support chatbot
100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each.
$356.40
Document Q&A (RAG)
50,000 questions a month with ~8,000 tokens of retrieved context and ~600 output tokens each.
$646.80
Coding agent
10,000 agent steps a month, ~40,000 input tokens each (70% read from the prompt cache) and ~2,000 output tokens.
$249.92

Pricing details

  • Prices shown are peak rates. Off-peak rates are half: peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday.
  • Vision input is not supported.

Estimate your DeepSeek V4 Pro bill

Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.