Cerebras · OpenAI-Compatible Engines
Cerebras has scheduled this model for deprecation on 17 August 2026.
A capable all-rounder — the sensible default for everyday assistant and agent work.
US$2.250 input / US$2.750 output
One price point recorded so far. The candlestick chart fills in as this model's rate changes — tracked automatically on every admin edit and weekly market sync.
Model id: zai-glm-4.7
Wafer-scale inference for open-weight models — the same OpenAI-compatible format as the rest of the gateway, at ~1,000–3,000 tokens/second.
Get an API key and point your first request at ApiSpi in minutes