Skip to main content

Which LLM does Creopus use?

Creopus runs a provider-fallback chain. Every tool uses the same default order:

Gemini 2.5 Flash → Cerebras → Claude Haiku 4.5

ProviderModelContextMax outputImages
Google Vertex AI (asia-south1)Gemini 2.5 Flash1M input65KYes
Cerebrasgpt-oss-120b128K shared40KNo
AnthropicClaude Haiku 4.5200K shared64KYes

If the primary provider is rate-limited, errors out, or the prompt exceeds its context window, the platform automatically retries on the next provider in the chain. Tools that require image understanding skip providers that cannot accept images.

The order is configurable per tool by environment variable, so an individual tool can be pinned or re-ordered without a release.