Model defaults

​

Setting the default

• Default text model — used by new Agent blocks.
• Default vision model — used when an Agent’s inputs include images.
• Default voice model — used for voice inputs.
• Default embedding model — used by Foundry Embed blocks and memory index spaces.

​

Per-Agent overrides

nora agents update ag_1 --set-model gpt-4o

​

Fallback models

• Primary: high-quality model (higher cost).
• Fallback: cheaper, faster model that’s usually good enough.

​

Cost defaults

• Default max cost per run — dollar cap.
• Default max tokens per run — token cap.

​

Choosing a default

• Higher-tier default (GPT-4o, Claude Opus, Gemini Pro) — new Agents work well out of the box. Higher cost until you tune down.
• Lower-tier default (GPT-4o-mini, Claude Haiku, Gemini Flash) — new Agents are cheap. You’ll upgrade individual Agents when quality demands it.

​

When defaults matter most

• Team onboarding — new engineers building Agents don’t have to decide upfront.
• Bulk operations — CI scripts that create many Agents don’t need model choice per creation.
• Templates — Flow templates shipped to your org use the workspace defaults.

​

Watching for drift

# Count Agents on the default model
default=$(nora settings models defaults --json | jq -r '.default_text_model')
for f in $(nora flows list --json | jq -r '.[].slug'); do
  count=$(nora flows get $f | jq --arg m "$default" '[.blocks[] | select(.kind=="agent" and .model==$m)] | length')
  echo "$f: $count Agents on default model"
done

​

Related

• Providers — the API keys behind the models.
• nora agents update --set-model — override per-Agent.
• Cost vs. quality — pick models by data, not guess.