Multimodal / Vision
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash by DeepSeek costs $0.3 per 1M input tokens and $1.2 output. It is available outside China via an official international API and OpenRouter. Last checked 2026-10-27.
DeepSeek · mit · 763.2B
$0.3 in · $1.2 out
Official API model id deepseek-flash is version DeepSeek-V4.1-Flash-1017. Input/output shown are peak cache-miss and peak output. Off-peak is half, including cache hit $0.003. Legacy names deepseek-v4-flash and deepseek-v4-flash-vision-exp are retired and billed at this Flash price. openrouter_from keeps the previous lowest OpenRouter input.
How to use it from outside China
- Call the official international API. https://api.deepseek.com
- Send requests through OpenRouter. https://openrouter.ai/deepseek/deepseek-v4.1-flash
- Weights are public. Download them from Hugging Face. https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
- Confirm the price on the source before you rely on it. Checked 2026-10-27. Pricing source
Usable outside China?
Official international API: https://api.deepseek.com
OpenRouter: https://openrouter.ai/deepseek/deepseek-v4.1-flash
Questions
Can I use DeepSeek V4.1 Flash from outside China?
Official international API: https://api.deepseek.com. OpenRouter: https://openrouter.ai/deepseek/deepseek-v4.1-flash.
How much does DeepSeek V4.1 Flash cost per 1M tokens?
$0.3 input and $1.2 output per 1M tokens. official. Checked 2026-10-27.
Is the DeepSeek V4.1 Flash API OpenAI-compatible?
Unknown — not on the record yet
Are DeepSeek V4.1 Flash weights open, and under which license?
Yes. License: mit.
Sources
https://api-docs.deepseek.com/quick_start/pricing
Weights: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
Related models
More from DeepSeek
Other vision models
Compare DeepSeek V4.1 Flash with DeepSeek V4.1 Flash 1017 · More vision · DeepSeek