Route Readiness
How B3IQ explains why a node or model is eligible or blocked for routed paid inference.
Route readiness is the public-safe diagnosis for whether a node can serve routed work. It combines node liveness, route health, protocol state, model profile policy, benchmark evidence, queue health, and customer gateway policy.
Public Diagnosis Endpoint
textGET /v1/public/nodes/:node_id/route-readiness?model=<model>
The response can include route blockers, model blockers, next actions, and operator prompts. It must not include tunnel IDs, local URLs, runtime IDs, prompts, outputs, request IDs, API keys, customer IDs, raw tokens, route secrets, or private tunnel details.
Gate Order
Blockers And Actions
| Blocker | Meaning | Operator action |
|---|---|---|
| Enrollment | Node is not fully enrolled | Complete managed enrollment |
| Heartbeat | Heartbeat is stale, missing, or offline | Bring host agent online and sync a fresh heartbeat |
| Runtime | Runtime is not ready or reachable | Start or configure runtime and rerun probe |
| Protocol/stake | Node is not registered, active, or stake-satisfied | Finish registration and stake after operator approval |
| Route tier | Profile tier is blocked for paid dispatch | Use or configure an approved route tier |
| Benchmark proof | Observed benchmark evidence is missing or stale | Run benchmark smoke and publish fresh evidence |
| Queue health | Queue is blocked or unhealthy | Clear runtime queue issue and publish heartbeat |
| Customer policy | Caller policy rejects model, price, route tier, or spend | Update policy or send an allowed request |
Earning Explanation
The operator-facing answer to "why am I not earning yet?" should be direct:
Paid routing requires more than an installed model. The node must be enrolled, online, route-ready, protocol registered, active, stake-satisfied, runtime-ready, model-installed, network-eligible, benchmark-observed, paid-route eligible, queue-healthy, and accepted by customer billing policy.
Stale Benchmark Prompts
If an otherwise eligible profile depends on stale observed benchmark evidence,
B3IQ should prompt the operator to rerun benchmark.smoke after runtime,
driver, model artifact, quantization, context, or queue-policy changes.