Modelsdeepseek-v4.1-flash

DeepSeek: DeepSeek V4.1 Flash

deepseek-v4.1-flash

DeepSeek-V4.1-Flash is the smallest member of DeepSeek’s new model architecture family and natively supports multimodal visual understanding. The architecture targets stronger capabilities, faster inference and greater throughput, with room to scale to larger model sizes.

Capabilities & limits

Model type: Vision Language
Input modalities
Output modalities
Context: 1,048,576tokens
Max output: 393,216tokens
Vision / images: Yes
Tools & function calling: Yes

Updated Sep 10, 2026

Pricing

Pay as you go. Rates depend on the provider route you use; below is reference pricing when available.

01:00–04:00, 06:00–10:00 UTC · Mon–Fri
- Uncached input tokens
  $0.3 / per 1M tokens
- Cache hit tokens
  $0.006 / per 1M tokens
- Output tokens
  $1.2 / per 1M tokens
Other times
- Uncached input tokens
  $0.15 / per 1M tokens
- Cache hit tokens
  $0.003 / per 1M tokens
- Output tokens
  $0.6 / per 1M tokens

One scenario is selected per request; prices from different rows are not added together. Within the selected scenario, the listed meter charges are added together.