Limits & billing
Operational caps the agent enforces at runtime, plus how credits and plans work. Design your tools and conversations against these numbers.
Runtime caps
Per-conversation and per-call limits enforced by the chat engine.
| Cap | Value | What happens on overrun |
|---|---|---|
| Tool result size | 8 KB | Result is truncated server-side (...truncated suffix) and the truncated value is what the agent sees. |
| Route timeout | 30s | The server-to-server fetch is aborted and the tool call returns a timeout error. |
| Steps per conversation | 20 | The agent stops generating further steps once the limit is reached (graceful stop, no error). |
| Tokens per conversation | 80,000 | The conversation is hard-stopped with a token_cap error. Start a new conversation to continue. |
| Idempotency key TTL | 24 hours | Duplicate execute-result calls with the same key return the original cached response instead of re-executing. |
Keep route/server-action handlers fast and their return values small — design for the 8 KB / 30s caps above, not just “concise.”
Rate limits
Enforced per endpoint via a sliding window. Exceeding a limit returns
429 Too Many Requests with a Retry-After header.
| Endpoint | Limit | Keyed by |
|---|---|---|
POST /api/v1/chat | 20 req/min | project + end-user |
POST /api/v1/chat (project ceiling) | 120 req/min | project |
POST /api/v1/execute-result | 60 req/min | project |
POST /api/v1/describe | 30 req/min | project |
| Auth endpoints (sign-in, OTP verify) | 20 req/min | IP |
| Sign-up | 5 attempts / 15 min | IP |
Models
The hosted chat engine currently runs on a single fixed model —
claude-sonnet-4-6 — for every project and plan. Per-project or
per-conversation model selection isn’t available yet.
The model-picker widget on the marketing homepage is illustrative of where this is headed, not a live setting — there’s no way to switch to Haiku or Opus today.
Credits & plans
Every plan is billed in credits, consumed per action regardless of model or token count:
| Action | Credits |
|---|---|
| Conversation start | 2 |
| Message | 1 |
| Tool call | 3 |
Plans differ in included credits and whether you can go over:
| Plan | Included credits | Period | Overage |
|---|---|---|---|
| Free | 500 | 30 days | Hard-capped — chat endpoint returns an error until reset, no extra billing. |
| Starter | 1,500 | 30 days | Hard-capped, same as Free. |
| Plus | 4,000 | 30 days | Allowed, $10 per 1,000 additional credits. Supports bring-your-own API key for unlimited usage. |
| Enterprise | Custom | 30 days | Custom — talk to sales . |
The credit period is a rolling 30-day window — it resets 30 days after the window last started, not on a fixed calendar date.
Full CLI reference: CLI Reference. Tool result/runtime behavior: Tool Files.