How do I choose a model?
Stackbone does not rank models for you. What it gives you is one place to set each model, a live catalogue to read, and eval suites to measure a swap once you have made it.
Three model ids come from your own project, and each is set in a different
place. The agent's reasoning model is the model you pass to
defineDeepAgent(...) in its index.ts, and it drives the main loop. A one-off
completion, embedding or image goes through stackbone.ai, where you pass
model on the call itself. Retrieval takes the model you pass on the
stackbone.rag call, and the rag.embeddingModel key in agent.yaml parses
but changes nothing. Guardrails and evals ask their own models, which you pick
in Studio settings rather than in code.
To compare candidates, read the catalogue. stackbone.ai.models.list() returns
whatever the provider reports for each model, which on OpenRouter includes
context_length and pricing. Every id uses the creator/model-name form, so
switching is a one-line edit.
Then measure the change. An eval suite runs your saved cases against the agent and reports a pass rate against a pass mark, and that number belongs in CI.
Read more
- Gateway: where each of those ids is set, and the one endpoint they all resolve through.
stackbone.ai: the catalogue call and everyai_*error code.- Testing and evals: how to measure a model swap.
- Which models can I use?: providers and the ids they resolve.