How a job spends AI credit
What leaves your machine, how each step reserves its cost, and where a job always stops.
Video in production
Until it is ready, this is the running order. Each step is also written out below, and you can try it in the simulator.
- Two balances
My account credit meters and the refill date.
- Sharing switch
Design-context sharing off, then on, with the preview of what is sent.
- One job
Motion graphic: reserve, use, return, twice.
- The stops
£2 and eight steps; uncertain outcome stops the loop.
You need
- A paid seat
You'll come away with
- Know the order credit is spent in
- Follow one job step by step
- Know the two limits that stop every job
Step by step
Know your balances
Each paid seat includes £5 of managed AI credit per UTC month, spent first and refilled on the 1st. Top-ups of £10, £25 or £50 are spent next and carry forward. My account shows both as meters.
Know what is sent
Nothing is sent until you tick Allow sending design context to OpenAI when I press Send, in Settings, Agent API. It is off by default, and Send stays disabled until you allow it. Then your message goes with the design intent and instructions, reference names and fingerprints (never file contents), the latest worksheet inspection and the results of tools the Agent runs. To see the context, open the Instructions tab and choose Preview.
Follow a step
Each step makes at most one tool call. Before it runs, credit is held; afterwards the hold settles to actual usage and the rest is returned. The app lists its rates under Settings, Agent API: per million tokens, £40 input, £4 cached input, £50 cache writes and £200 output, including reasoning.
Know where it stops
A job stops at £2 or eight steps, whichever comes first. It also stops when an outcome is uncertain, and it never retries a CAD step on its own.
Try it here.
The limits and rates are the app's own. Token counts and held amounts are examples, so each cost is calculated from example usage, not measured.
YOUFind a 50 mm square tube, then make me a 100 × 50 × 25 mm block.
Balances before
- Included this month
- £5.00
- Top-ups
- £0.00
- Job cap
- £2.00 or 8 steps
Illustration
What it won't do
- Managed AI uses OpenAI with global processing; see the privacy notice.
- Unused included credit does not roll over; top-ups do.
- A cancelled step may still incur a charge if it was already running.
If you see a message
Licensing request refused (…). Check credentials, seat availability and subscription.
Activate a paid seat and refresh credit balance in Agent settings.
Activate or renew a Solidworks Agent seat at paracrux.com first
Managed inference stopped: …. Usage and any unresolved hold remain recorded.
Provider returned HTTP …. No automatic retry.
OpenAI sign-in did not complete. Try Connect again.
Connect ChatGPT in Agent settings first
Codex turn did not complete; account usage may have occurred. No automatic retry.
Selected model is unavailable. Refresh models and choose another.
A refund affects credit already spent or reserved. AI spending is paused; contact support to reconcile your balance.
Covers: Managed AI credit, What leaves your workstation, Job limits. See the full index