← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
DeepSeek V4 Flash Vision Exp Pricing
DeepSeek · deepseek-deepseek-v4-flash-vision-exp
Input / 1M tokens
$0.216
Output / 1M tokens
$0.647
Context window
1,048,576 tokens
≈ 1,398 pages of text
Max output
262,144 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0005
1,000 requests / month$0.5174/mo10,000 requests / month$5.17/mo100,000 requests / month$51.74/moEstimate your own workloadOpens the calculator with DeepSeek V4 Flash Vision Exp 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
Supports 1M-token multimodal contexts at low per-token cost, enabling high-volume document and image processing workloads.
The business tradeoff
Experimental status implies potential instability in reasoning consistency; open-weights hosting shifts performance and reliability responsibility to the deployer.
Cheaper from DeepSeek
Head-to-head
Vendor list rates, as of Sep 28, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.