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

# Meliai Pricing: Energy-Based and Credit-Based Billing

> Meliai bills per request: energy consumption (kWh) or credits, depending on the model. Every response includes a billing_cost field with exact charges.

Meliai takes a transparent, per-request approach to billing: every API response includes a `billing_cost` field that tells you exactly what was charged for that call — no aggregated end-of-month surprises. Pricing is either energy-based (measured in kilowatt-hours) or credit-based depending on the model, and you can always see which mode applied by inspecting the `paid_with` field.

## Billing modes

Meliai supports two billing modes:

<CardGroup cols={2}>
  <Card title="Energy billing" icon="bolt" href="/guides/environmental-impact">
    Charges are calculated from the actual energy consumed by the inference workload, measured in **kWh**. This maps directly to the `environment_impact.energy_kwh` value in the response and is the default for most text-generation models.
  </Card>

  <Card title="Credit billing" icon="coins" href="/concepts/models">
    Some models are billed in **Meliai credits** — a fixed unit that abstracts over provider-specific pricing. Credits are pre-purchased and drawn down per request.
  </Card>
</CardGroup>

Every response body includes a `billing_cost` object so you always know what was charged:

```json theme={null}
{
  "billing_cost": {
    "energy": "0.0008",
    "credits": "0.0",
    "paid_with": "energy"
  }
}
```

| Field       | Type   | Description                                                               |
| ----------- | ------ | ------------------------------------------------------------------------- |
| `energy`    | string | kWh consumed by this request (as a decimal string).                       |
| `credits`   | string | Credits deducted for this request. `"0.0"` when billing mode is `energy`. |
| `paid_with` | string | Either `"energy"` or `"credits"` — tells you which balance was drawn.     |

## Routing and cost

Your choice of routing flavor directly affects how much each request costs:

| Flavor     | Cost impact                                               |
| ---------- | --------------------------------------------------------- |
| `balanced` | Moderate — trades cost against speed and eco impact       |
| `speed`    | Higher — fastest providers aren't always the cheapest     |
| `price`    | **Lowest real-time cost** — the default for embeddings    |
| `eco`      | Moderate — greener providers may not be the cheapest      |
| `batch`    | **Deepest discount** — async processing at off-peak rates |

Append the appropriate suffix to your model ID to activate a flavor:

```python theme={null}
# Minimise cost for a real-time request
model = "qwen/qwen3-235b-a22b:price"

# Maximise discount for an offline workload
model = "qwen/qwen3-235b-a22b:batch"
```

<Tip>
  Use `:batch` routing with the [Batches API](/api-reference/batches) for high-volume offline workloads such as document processing or dataset annotation. Batch jobs are queued and processed during low-demand windows, giving you the lowest per-token cost available on the platform.
</Tip>

## Free trial

You can start using Meliai without a credit card. New accounts receive a free usage allocation so you can explore the API and evaluate models before committing to a paid plan.

<Info>
  View current per-model pricing, top up your energy balance or credits, and manage your billing plan at [https://meliai.ai/pricing](https://meliai.ai/pricing).
</Info>