Cerebras
2 modelsCerebras runs open-weight models on the Wafer-Scale Engine for among the fastest inference in the industry. This page lists the Cerebras models in the directory with per-million-token pricing, context window sizes, output limits, and supported features.
cerebras.aiAPI base: https://api.cerebras.ai/v1
2 of 2 modelsShowing 2 of 2 models from 1 provider
GPT OSS 120b gpt-oss-120b | $0.35 | $0.75 | - | - | - | - | - | 131.1K | - | 32.8K | ReasoningToolsStructured outputTemperature | Text | Text | Aug 6, 2025 | - | - | - | @ai-sdk/cerebras | CEREBRAS_API_KEY | https://api.cerebras.ai/v1 | |
Qwen 3.8 27B qwen-3.8-27b | $0.99 | $1.49 | - | - | - | - | - | 65.5K | - | 32.8K | ReasoningToolsStructured outputFilesTemperature | ImageText | Text | - | - | - | - | @ai-sdk/cerebras | CEREBRAS_API_KEY | https://api.cerebras.ai/v1 |