Cerebras launches Qwen3-235B, achieving 1.5k tokens per second
World's fastest frontier AI reasoning model now available on Cerebras Inference Cloud Delivers production-grade code generation at 30x the speed and 1/10th the cost of closed-source alternatives Paris, July 8, 2025 – Cerebras Systemstoday announced the launch of Qwen3-235B with full 131K context support on its inference cloud platform. This milestone represents a breakthrough in AI model performance, combining frontier-level intelligence with unprecedented speed at one-tenth the cost of closed