← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
DeepSeek V4 Flash Pricing
DeepSeek · deepseek-deepseek-v4-flash
Input / 1M tokens
$0.089
Output / 1M tokens
$0.177
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)$0.0002
1,000 requests / month$0.1772/mo10,000 requests / month$1.77/mo100,000 requests / month$17.72/moEstimate your own workloadOpens the calculator with DeepSeek V4 Flash preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Jun 2026. Each step marks a price change — hover a point for the exact date and rate.
What it excels at
Handles high-volume text and coding workloads efficiently with a 1M-token context window at low per-token cost.
The business tradeoff
Performance depends on user-hosted inference; lacks managed ecosystem tooling and may show higher latency variance than closed providers.
Cheaper from DeepSeek
Head-to-head
Vendor list rates, as of Sep 14, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.