DeepSeek V4.1 Flash

10 September 2026DeepSeek

Available on MiniRouter for text generation. DeepSeek reports stronger coding results than V4 Flash.

DeepSeek V4.1 Flash is available on MiniRouter as . The model page has current pricing, provider routes and API setup.

About the model

Architecture: 552B MoE. Causal Encoder–Decoder; 8B active input parameters, 16B output.
Model limits: 1M context / 384K output. Text and image input. MiniRouter supports text only.
DeepSeek API ID: deepseek-flash. MiniRouter: .
Weights: MIT license. Open weights and technical report.

Publisher-listed API price phases in US dollars per million tokens.
Phase	Input / 1M	Output / 1M	Blended / 1M	Effective	Source
Off-peak	$0.15	$0.60	$0.2625	Sep 10, 2026 – open-ended	DeepSeek ↗
Peak · weekdays 01–04 / 06–10 UTC	$0.30	$1.20	$0.525	Sep 10, 2026 – open-ended	DeepSeek ↗

Benchmark	Reported result	Reported by	As of	Source
DeepSWE v1.1	74.2%	DeepSeek	Sep 10, 2026	Announcement ↗
Terminal Bench 2.1	90.6%	DeepSeek	Sep 10, 2026	Announcement ↗
Terminal Bench 3.0	30.0%	DeepSeek	Sep 10, 2026	Announcement ↗
Terminal Bench 4.0	31.2%	DeepSeek	Sep 10, 2026	Announcement ↗
GPQA Diamond	90.9%	DeepSeek	Sep 10, 2026	Announcement ↗
CyberGym	88.1%	DeepSeek	Sep 10, 2026	Announcement ↗

DeepSeek's API replaces V4 Flash and V4 Flash Vision Exp with V4.1 Flash. The deepseek-v4-pro alias switches on September 14 at 04:00 UTC.

Publisher prices apply from September 10 at 04:00 UTC. Cached input: $0.003/M off-peak, $0.006/M peak. See the model page for MiniRouter's rates.

GPQA Diamond: 90.9%, versus V4 Pro's 92.4% in DeepSeek's results.

Compare published results in the model rankings and coding benchmarks, or read more model releases.

For MiniRouter product updates, visit the changelog.