Cerebras
Fast AI inference on wafer-scale chips, from thousands of tokens per second
Launched 1 week agocerebras.ai
Do you work on Cerebras?
This listing is unclaimed. Claim it for free to edit the details, add screenshots and reply to reviews.
About Cerebras
Cerebras Inference serves open-weight language models such as Llama, Qwen and GPT-OSS on its wafer-scale CS-3 chips. It is aimed at developers who need very fast model responses through an OpenAI-compatible API. The company reports 1,800 to 2,600 output tokens per second on Llama 3.1 8B and several hundred on 70B models. Its CS-4 system is described as delivering up to 30x faster inference than GPUs. A free tier includes one million tokens per day without a credit card, and paid plans use pay-per-token pricing.
Reviews
From people who have used it. One review per person, checked by a human.
No reviews yet. Be the first to say something useful.
