Skip to content
NerdLevelTech

DeepSeek

DeepSeek V4.1 Flash

Open weights at a fraction of frontier prices

Open weightsNewReleased: October 17, 2026Self-hostingHigh volumeVerified: October 24, 2026

What it is

DeepSeek’s Flash tier: a 1M-token context window, thinking on by default, vision input and open weights. Peak API pricing is $0.30/$1.20 per 1M tokens; off-peak is half.

NLT take

The best price-to-capability ratio on this list, and the only one you can also run yourself. Use the API for convenience, the weights for privacy.

Before you switch

Peak and off-peak prices differ by 2×, so a nightly batch and a daytime agent do not cost the same. Pin the timezone in your cost model.

Cost for a real task

The same task on every model: 50,000 input tokens and 10,000 output tokens, at the base tier.

Task cost

$0.027

50K input + 10K output tokens

Input, per 1M
$0.30
Output, per 1M
$1.20
Cached input, per 1M
$0.006

Peak rates. Off-peak is half: $0.15 input / $0.60 output. Peak is 01:00–04:00 and 06:00–10:00 UTC on weekdays.

Pricing source: DeepSeek models and pricing

Specs

Maker
DeepSeek
Licence
Open weights
Released
October 17, 2026
Context window
1,000,000 tokens
Max output
384,000 tokens
Input / output
Text · Image → Text

Also known as: deepseek-flash · DeepSeek-V4.1-Flash-1017 · deepseek-v4.1-flash:1017-cloud

Watch it in action

Hands-on videos from creators we trust. They open on YouTube; we do not host or re-upload them.

From our coverage

Articles about this model or its family. A “Background” tag means we have not covered this exact release yet.

Sources & model links

Every number on this card traces back to one of these links. The maker page proves the positioning, the pricing page proves the rates, the Hugging Face repo proves the weights exist, and the Ollama page proves a local tag.

Official

Open weights

Run locally