Baseten
@baseten
Inference is everything.
Joined March 2021
340 Following 10.2K Followers
We serve Qwen3-TTS on vLLM-Omni at $3 per 1M characters. That's 90% lower in cost than comparable closed-source TTS APIs.
Our engineers optimized a single-replica serving stack to get there. Details on the optimized stack and cost per concurrent stream here.
Show more
