Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support.
Input: Text, Image
Output: Text
Providers
deepinfra
Credits
Context41k
Max Output41k
Input$0.080/1M
Output$0.290/1M
Cache Read—
Cache Write—
Quick Start
Use Qwen3 30B A3B through Helicone's AI Gateway with automatic logging and monitoring.