DeepSeek v4.1 Flash is now available for internal beta testing
DeepSeek V4.1 Flash is now available for internal beta testing. It uses a new model architecture, with native multimodal support, stronger capabilities, faster speed, and lower cost.
Keep the `base_url` unchanged and set the model name to `deepseek-v4.1-flash-expires-on-0910` to use it. Pricing is currently the same as `deepseek-v4-flash`, with an account-level rate limit of 20 concurrent requests.
lower cost lol how -- effective price is like 4 cents / m in on openrouter with cache hits.
It is more token efficient I believe
Where can I test it ?
Get an account at platform.deepseek.com and configure your agent with the model name deepseek-v4.1-flash-expires-on-0910, you have to manually configure the model, it does not automatically show up.
based
Wow, it's fast.
speed matters way more than ppl think tbh
id take a slightly worse model thats 2x faster for most product use cases
can't wait to test it out :P