Usage Limits
Atom itself has no message limit after activation. The limits you may run into come from Codex, Claude Code, or the provider you use through OpenCode.
What uses your allowance
Every message you send and every response Atom receives consumes tokens. Some things use more than others.
- Simple edits like renaming a clip or adding a marker use very little.
- Multi-step automations like organizing media or rebuilding part of a sequence use a moderate amount.
- Large project scans where Atom reads many bins, sequences, tracks, and clips use more.
- Long conversations where you build on context over many messages add up cumulatively.
Staying efficient
- Be specific. Targeted prompts use fewer tokens than vague ones. “Add a one-second cross-dissolve between the selected clips” is more efficient than “make the edit better.”
- Start fresh when the context gets stale. Long conversations accumulate tokens. If you’ve switched tasks, start a new chat.
- Use skills for repetitive work. Saved prompts reduce back-and-forth.
- Work in focused sessions. Batching related edits into one session is more efficient than scattering single requests throughout the day.
Provider limits
Anthropic
If you use Claude Code, your limits come from Anthropic. Depending on how you sign in, that usually means:
- an Anthropic plan that includes Claude Code, or
- Anthropic API billing
OpenAI
If you use Codex, your limits come from OpenAI. Depending on how Codex is configured on your machine, that usually means:
- an OpenAI plan that includes the AI features Atom uses,
- a ChatGPT Business or Enterprise account, or
- OpenAI API billing
OpenCode
If you use OpenCode, limits and billing come from the model provider configured in OpenCode.
Subscription plans often have rolling limits, while API billing is typically pay-per-token. Check the selected provider’s dashboard for current usage and reset timing.