Devin Desktop can run AI Reserve models — through the third-party agents it
hosts, not through Devin itself. Its
Agent Command Center runs ACP agents such
as Codex CLI and Claude Code inside the editor. Each hosted agent reads its own
configuration, so once you’ve connected it to AI Reserve it routes through the
gateway exactly as it does standalone — every request metered and billed on
your key.
Devin’s own agents (cloud Devin, Devin Local, the Devin CLI) are the
exception: they run exclusively on Cognition’s managed models. Cognition’s
enterprise FAQ states
Devin “does not currently support third-party LLM API keys”, and the app has
no base-URL or key field — there is nothing to configure on Devin itself.
Two steps:
- Connect the agent to AI Reserve — follow the Codex or
Claude Code guide. Nothing here is Devin-specific
(OpenCode is hosted too and works the same way).
- Add the agent in Devin Desktop — open the Agent Command Center and add
Codex CLI or Claude Code, following
Cognition’s ACP guide. ACP agents are
available on Pro, Max, and Teams plans; Enterprise admins can ask their
Cognition account team to enable them.
Prefer config files over shell exports. Agents launched from Devin’s GUI
may not inherit your shell profile. Codex reads ~/.codex/config.toml, which
already persists; for Claude Code, put the variables in the env block of
~/.claude/settings.json (the one-click connect page writes that block for
you). Devin can also inject per-agent variables — the Agents tab, or
devin.acp.agentEnv.<agent> in its settings.
