← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
DeepSeek V4.1 Flash 1017 Pricing
DeepSeek · deepseek-deepseek-v4-1-flash-1017
Input / 1M tokens
$0.150
Output / 1M tokens
$0.600
Context window
1,048,576 tokens
≈ 1,398 pages of text
Max output
393,216 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0004
1,000 requests / month$0.42/mo10,000 requests / month$4.20/mo100,000 requests / month$42.00/moEstimate your own workloadOpens the calculator with DeepSeek V4.1 Flash 1017 preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Handles 1M-token contexts and vision inputs at very low cost. Suitable for high-volume document and multimodal processing workloads.
The business tradeoff
Open-weights deployment introduces hosting and latency variance. Reasoning depth trails closed flagship models on complex multi-step tasks.
Cheaper from DeepSeek
Head-to-head
Vendor list rates, as of Oct 17, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.