Kurahi models
Model discovery, scanning, and configuration (default model, fallbacks, auth profiles).
Related:
- Providers + models: Models
- Provider auth setup: Getting started
Common commands
Section titled “Common commands”kurahi models statuskurahi models listkurahi models set <model-or-alias>kurahi models scankurahi models status shows the resolved default/fallbacks plus an auth overview.
When provider usage snapshots are available, the OAuth/token status section includes
provider usage headers.
Add --probe to run live auth probes against each configured provider profile.
Probes are real requests (may consume tokens and trigger rate limits).
Use --agent <id> to inspect a configured agent’s model/auth state. When omitted,
the command uses KOLO_AGENT_DIR/PI_CODING_AGENT_DIR if set, otherwise the
configured default agent.
Notes:
models set <model-or-alias>acceptsprovider/modelor an alias.- Model refs are parsed by splitting on the first
/. If the model ID includes/(OpenRouter-style), include the provider prefix (example:openrouter/moonshotai/kimi-k2). - If you omit the provider, Kurahi treats the input as an alias or a model for the default provider (only works when there is no
/in the model ID).
models status
Section titled “models status”Options:
--json--plain--check(exit 1=expired/missing, 2=expiring)--probe(live probe of configured auth profiles)--probe-provider <name>(probe one provider)--probe-profile <id>(repeat or comma-separated profile ids)--probe-timeout <ms>--probe-concurrency <n>--probe-max-tokens <n>--agent <id>(configured agent id; overridesKOLO_AGENT_DIR/PI_CODING_AGENT_DIR)
Bench and the KODA tested catalogue
Section titled “Bench and the KODA tested catalogue”kurahi models tested [--residency jp] [--min-score 70] [--tested-only] [--json]kurahi models bench --model <provider/model> [--quick-model <provider/model>] [--only <ids>] [--max-tokens <n>]kurahi models bench-merge <bench-report.json...> --out <dir> [--update-catalogue <file>]models tested prints the shipped catalogue: scores per axis, residency, cost per resident-hour and
the date of the last benchmark. models bench runs the resident task suite under a token cap and
writes a signed report with evidence bundles. See KODA tested models.
Aliases + fallbacks
Section titled “Aliases + fallbacks”kurahi models aliases listkurahi models fallbacks listAuth profiles
Section titled “Auth profiles”kurahi models auth addkurahi models auth login --provider <id>kurahi models auth setup-tokenkurahi models auth paste-tokenmodels auth login runs a provider plugin’s auth flow (OAuth/API key). Use
kurahi plugins list to see which providers are installed.
Notes:
setup-tokenprompts for a setup-token value (generate it withclaude setup-tokenon any machine).paste-tokenaccepts a token string generated elsewhere or from automation.