Skip to main content
providers tells Managed Research which provider capability a run may use. It is separate from agent_model.

​
Public example

providers=[{"provider": "openrouter"}]
This binds OpenRouter provider capability for the run. The model still comes from agent_harness and agent_model when you choose them explicitly.

​
Provider bindings

Provider bindings can include non-secret config and limits: 
providers=[
    {
        "provider": "openrouter",
        "config": {"allowed_models": ["anthropic/claude-sonnet-4-6"]},
        "limit": {"max_spend_usd": 10.0},
    }
]
Do not put API keys or raw secrets in provider config. Use supported credential setup so backend preflight can verify availability safely.

​
Availability

Backend preflight is authoritative for:
  • missing credentials
  • provider launch availability
  • budget and entitlement blockers
  • unsupported provider/model combinations
  • required capability gaps
If a launch fails, read Preflight and Errors.