> ## Documentation Index
> Fetch the complete documentation index at: https://modelrunner.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Quotas and capacity

> Per-account deployment and worker limits, the platform-wide capacity ceiling, and what to do when you hit either.

Two different limits can refuse a deployment: **your account's quota**, and the **platform's total serverless capacity**. They fail differently and they need different responses.

## Your quota

Defaults for a beta account:

| Limit                                      | Default |
| ------------------------------------------ | ------- |
| Live deployments per account               | 2       |
| Max workers on one deployment              | 3       |
| Sum of max workers across your deployments | 5       |

The third is the one people trip over: it is the **sum of configured `workersMax`**, not the number of workers currently running. Two deployments at `workersMax: 3` each already total 6 and exceed the cap, even if both are scaled to zero and costing nothing.

Exceeding any of them returns a `400` naming the limit:

```json theme={null}
{ "error": "Your total max workers across deployments is capped at 5 (contact support to raise it)" }
```

The same checks run on **update**: raising `workersMax` on an existing deployment re-evaluates your totals. Resume does not re-check them — a paused deployment never gave its share back, so there is nothing to re-evaluate.

<Tip>
  Delete deployments you are done with rather than leaving them paused. A paused deployment still occupies your deployment count and its `workersMax` still counts against your worker total.
</Tip>

To raise your limits, email [support@modelrunner.ai](mailto:support@modelrunner.ai) with what you are running and the scale you need.

## Platform capacity

Serverless GPU capacity is finite and shared. When the platform-wide ceiling is reached, **creating** a deployment returns **409**:

```json theme={null}
{ "error": "The platform is at serverless capacity right now. Try a lower max-workers value or try again later." }
```

Raising `workersMax` on an existing deployment hits the same ceiling but reports it as a **400**:

```json theme={null}
{ "error": "The platform is at serverless capacity right now; try again later." }
```

This is not about your account — you can be well inside your quota and still get it. What to do:

* **Ask for fewer workers.** `workersMax: 1` frequently fits when `3` does not, and scale-to-zero means a lower ceiling costs you nothing when idle.
* **Retry later.** Capacity frees up as other deployments drain.
* **Do not retry in a tight loop.** The answer will not change within seconds, and the queue API's [rate limits](/docs/api-reference/request-semantics#rate-limits) apply here too.

## GPU availability

Capacity is also per-SKU. Each GPU row in the catalog carries an `availability` badge, refreshed hourly:

| Badge             | What it means                                                     |
| ----------------- | ----------------------------------------------------------------- |
| `high` / `medium` | Workers should start promptly.                                    |
| `low`             | Capacity is tight; workers may sit `throttled` before they start. |
| `none`            | No capacity for this SKU right now. Pick another.                 |

A `throttled` worker on the [workers panel](/docs/guides/serverless-gpus/lifecycle#the-workers-panel) is this problem showing up at runtime: the deployment is fine, there is simply nowhere to place the worker at that moment. Throttled workers are not billed.

If a SKU you depend on sits at `low` or `none` repeatedly, deploy against a different one — the catalog spans several VRAM tiers, and a job that fits in 48 GB does not need to wait for 80.

## Other limits worth knowing

| Limit                  | Value                                       |
| ---------------------- | ------------------------------------------- |
| Submit body size       | 10 MB — pass a URL for anything larger      |
| Environment variables  | 32 per deployment, values ≤ 4096 characters |
| Concurrent log streams | 5 per account                               |
| Execution timeout      | 5 seconds to 2 hours, per deployment        |
| Idle timeout           | 1 to 60 seconds                             |

Balance limits are covered separately in [Billing](/docs/guides/serverless-gpus/billing) — a credit hold you cannot cover refuses creation with a `402`, which is a funding problem rather than a quota one.