Cerebras Inference
./ThinkWafer-scale inference API serving open models at very high tokens per second
OpenAPI
$ protocol support
[✗]MCP Server
[✓]OpenAPI Spec
[✗]Skill File
[✗]llms.txt
[✗]Structured Feed
$ payment protocols
none documented — this service is not reachable over an agent payment protocol
$ agent access
authAPI Key
onboardingPartial — dashboard signup, then API key
tosNeutral — no bot restrictions
webhooksNo
free tierYes
billingpay-per-token
#llm#fast-inference#open-models
https://cerebras.ai/inference
// run this service? claim this listing · suggest an edit