Routing
Models & routing
Code routes by slot, not model — the registry resolves a slot to a concrete model per call and records it on every run. Multi-provider by design; the judge slot never falls back (one eval label = one model).
Slots
judgeno fallback
Per-criterion LLM-as-judge scoring (generateObject, one call per criterion)
Default
claude-opus-4-7
eval integrity — one label, one model
reportfallback
Narrative report generation over scored results
Default
claude-sonnet-4-6
↳ gemini-2.5-pro → gemini-2.5-flash
utilityfallback
Cheap structured helper tasks (classification, extraction, titles)
Default
gemini-2.5-flash
↳ claude-haiku-4-5
Model catalog
| Model | Provider | Context | In /1M | Out /1M | Capabilities |
|---|---|---|---|---|---|
| claude-opus-4-7 | anthropic | 200K | $15.00 | $75.00 | streamingtoolsstructured-outputvisionprompt-cache |
| claude-sonnet-4-6 | anthropic | 200K | $3.00 | $15.00 | streamingtoolsstructured-outputvisionprompt-cache |
| claude-haiku-4-5 | anthropic | 200K | $1.00 | $5.00 | streamingtoolsstructured-outputvisionprompt-cache |
| gemini-2.5-pro | 1M | $1.25 | $10.00 | streamingtoolsstructured-outputvisionthinking | |
| gemini-2.5-flash | 1M | $0.30 | $2.50 | streamingtoolsstructured-outputvisionthinking | |
| gpt-5.5-pro | openai | 1M | $30.00 | $180.00 | streamingtoolsstructured-outputvisionprompt-cache |
| gpt-5.5 | openai | 1M | $5.00 | $30.00 | streamingtoolsstructured-outputvisionprompt-cache |
| gpt-5.4-mini | openai | 400K | $0.75 | $4.50 | streamingtoolsstructured-outputvisionprompt-cache |
| gpt-5.4-nano | openai | 400K | $0.20 | $1.25 | streamingtoolsstructured-outputvisionprompt-cache |