Skip to main content
Managed Research supports two public harnesses:
  • codex
  • opencode_sdk
Model compatibility is harness-specific. Public model IDs are not the same thing as launch entitlement. Backend preflight remains authoritative for the caller’s plan, Beta Access state, provider readiness, and budget limits.

​
Launch availability

AccessWhat it allows
Freelite, directed_effort, standard models, and one-time Managed Research credits.
Pro / TeamPaid GA model bundle and higher included usage.
Any plan + Beta Accessopen_ended_discovery, heavy, and all-model access.
lite and heavy describe run depth and coordination limits. They do not mean “smaller model” and “bigger model.” Choose the model explicitly when a harness supports model selection.

​
Codex harness

Model IDReasoning effort supportLaunch accessDefault
gpt-5.3-codexmediumBeta Access; worker/engineer roles onlymedium
gpt-5.3-codex-sparkmediumStandardmedium
gpt-5.4medium, highBeta Accessmedium
gpt-5.4-minilow, medium, highStandardmedium
gpt-5.4-nanolowStandardlow
gpt-oss-120bhighStandardhigh
Example: 
run = client.runs.start(
    "Review the repo and leave evidence for the smallest safe fix.",
    host_kind="daytona",
    work_mode="directed_effort",
    providers=[{"provider": "openrouter"}],
    agent_harness="codex",
    agent_model="gpt-5.4-mini",
    agent_model_params={"reasoning_effort": "medium"},
)

​
OpenCode SDK harness

Model IDReasoning effort supportLaunch access
anthropic/claude-sonnet-4-6None in the catalogBeta Access
anthropic/claude-haiku-4-5-20251001None in the catalogStandard
x-ai/grok-4.1-fastNone in the catalogStandard
moonshotai/kimi-k2.6None in the catalogStandard
Example: 
run = client.runs.start(
    "Review the repo and propose the smallest high-impact fix.",
    host_kind="daytona",
    work_mode="directed_effort",
    providers=[{"provider": "openrouter"}],
    agent_harness="opencode_sdk",
    agent_model="anthropic/claude-haiku-4-5-20251001",
)

​
Source of truth

The backend-owned Managed Research model catalog is the source of truth. The generated SDK enum in managed-research mirrors public model IDs, but backend preflight is the final authority for launch availability.