← All models
Balanced — strong quality at a mid priceOpen Weights
DeepSeek V4 Pro 0813 Pricing
DeepSeek · deepseek-deepseek-v4-pro-0813
Input / 1M tokens
$1.05
Output / 1M tokens
$3.15
Context window
1,048,576 tokens
≈ 1,398 pages of text
Max output
384k tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0025
1,000 requests / month$2.52/mo10,000 requests / month$25.19/mo100,000 requests / month$251.86/moEstimate your own workloadOpens the calculator with DeepSeek V4 Pro 0813 preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Aug 2026. Each step marks a price change — hover a point for the exact date and rate.
What it excels at
Handles extended context and large outputs effectively. Performs well on coding and technical reasoning benchmarks relative to its price tier.
The business tradeoff
Quality and latency vary with self-hosted deployment. High maximum output length increases total cost for generation-heavy workloads.
Cheaper from DeepSeek
Head-to-head
Vendor list rates, as of Sep 11, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.