Pricingby GlyphCerebras
Inference host · 2 models · 2 priced routes · cerebras.ai
Models on Cerebras
| Model | In / out per 1M | Vs headline | |
|---|---|---|---|
| $0.35 / $0.75+2587% vs headline | +2587% | fp16 · gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. | |
| $0.99 / $1.49+17% vs headline | +17% | fp16 · Qwen3.8 27B is an open-weight dense vision-language model from Qwen. |
About Cerebras
Cerebras Systems Inc., headquartered in Sunnyvale, California, develops semiconductors, supercomputers, and related software to power artificial intelligence deep-learning applications such as inference engines.