DeepSeek
FreeBasic
DeepSeek V4.1 Flash
deepseek-v4.1-flash
The new ultra-affordable DeepSeek: CED architecture, 1M tokens, solid coding and reasoning.
Technical Specifications
| API Identifier | deepseek-v4.1-flash |
|---|---|
| Plans | Free Basic |
| Maximum Context | 1M tokens |
| Vision (images) | ✓ Yes |
| Native Web Access | No |
| Image Generation | No |
| Input Cost | $0.011 / M tokens |
| Output Cost | $0.72 / M tokens |
Overview
DeepSeek V4.1 Flash is a sparse mixture-of-experts model, the first built on DeepSeek's new Causal Encoder-Decoder (CED) architecture. It activates only 8B parameters on input and 16B on generation, which makes it extremely cheap, with a 1-million-token context. It is the model most used by OpenRouter's automatic routers; on Mingo, it covers coding and reasoning on Free and Basic.
Strengths
Rock-bottom priceCoding and reasoning1M-token context
Ideal Use Cases
Free coding assistant
Write, explain and fix code at no extra cost.
Step-by-step reasoning
Solve a logic or math exercise with detailed steps.
Pricing
Input Tokens
$0.011
per million tokens
Output Tokens
$0.72
per million tokens
Related Models
Frequently Asked Questions
Which Mingo plan gives access to DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is included in the following Mingo plans: Free, Basic. Mingo's router selects it automatically when it is the best fit for your request, and you can also pick it manually.
What is the difference between DeepSeek V4.1 Flash and V4 Flash?
V4.1 Flash introduces the CED architecture and accepts image input. It keeps a very low price while improving quality on coding and reasoning.
Use DeepSeek V4.1 Flash on Mingo
DeepSeek V4.1 Flash and 130+ other models in one subscription: Mingo picks the best one for every question.
Try Mingo for free