Skip to content
trending

AI Model Atlas / DeepSeek

DeepSeek V4.1 Flash

One million input tokens cost $0.051 and one million output tokens $0.57. Context window: 1M tokens, about 1,748 A4 pages.

Data from 11 November 2026 API identifier: deepseek/deepseek-v4.1-flash

What it costs in practice

Pricing per million tokens doesn't mean anything to anyone, so I convert it to three tasks that people actually give to models. The usage assumptions are listed for each row so you can verify them.

TaskInputOutputCost
1500-word articlebrief plus finished text in English 1,500 tokens 2,200 tokens $0.0013
100 chat queries700 tokens per question and 400 per answer 70,000 tokens 40,000 tokens $0.03
Hour of work with an agentagent reads repository and writes fixes 250,000 tokens 30,000 tokens $0.03
The calculation does not include tax, intermediary markup, or context caching, which with repeated prompts can cut input costs by several dozen percent.

Technical details

ProviderDeepSeek
Modalitiestext + image → text
Context window1M tokens (~1,748 A4 pages)
Maximum response944k tokens
Step-by-step reasoningyes
Tool callingyes
Forced JSON formatyes
Knowledge cutoffnot specified
Cache read$0.018 per million
Content moderationno extra filter

How it compares to the rest

The database contains 469 models. In terms of input pricing DeepSeek V4.1 Flash is more expensive than 9 percent of paid models. A longer context window is available in 54 models.

Input price history

2026-09-11 · $0.152026-11-11 · $0.051

The chart shows the price of a million input tokens on consecutive measurement days. History starts on the day I launched the atlas and grows with each day. I don't backfill data.

Alternatives at a similar price

Models from other providers whose cost for the same article comes out closest.

ModelInput / MOutput / M1500-word articleContext
Hy3Tencent $0.13 $0.53 $0.0014 262k
Qwen3 30B A3BQwen (Alibaba) $0.12 $0.50 $0.0013 41k
Nemotron 3.5 Super VLNVIDIA $0.15 $0.47 $0.0013 1M
Qwen3.8 Omni FlashQwen (Alibaba) $0.15 $0.47 $0.0013 1M

Compare DeepSeek V4.1 Flash with another model or go back to the full database 469 models.

// site map
Quantslant in numbers 1,427posts in archive26news from the last 7 days18video models in the observatory
🎬 AI Video Benchmarks: Higgsfield DoP vs OpenAI Sora • Higgsfield vs Runway Gen-3 • AI Video Credit Calculator
× ‹ enlarge ›