Cerebras adds Qwen 3.8 27B at 1500 tokens/s

Qwen 3.8 27B available on Cerebras at 1500 tokens/s

Cerebras now serves Qwen 3.8 27B on its public inference endpoint at ~1500 tokens/s. Free tier gets 64k context; paid tier goes up to 128k. The other public model is OpenAI GPT OSS 120B at ~3000 tokens/s. The post doesn't spell out pricing or latency for Qwen 3.8 27B beyond rate limits and pay-as-you-go.