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

# Models and pricing

> Use Model Square to filter models, read simple tags, and understand pricing.

Model Square is the main place to choose models and understand prices. Billing handles balance and top-ups; Usage handles per-request troubleshooting.

<Columns cols={3}>
  <Card title="Filter models" icon="sliders-horizontal">
    Search by provider, tag, and keyword.
  </Card>

  <Card title="Compare prices" icon="chart-no-axes-combined">
    Review input, output, cache, per-call, or dynamic pricing.
  </Card>

  <Card title="Copy model names" icon="copy">
    Copy the exact model name shown in Model Square for the `model` field.
  </Card>
</Columns>

## Page information

Model Square usually shows:

* Model name: the exact value to use in the API `model` field.
* Provider: where the model or compatible channel comes from.
* Tags: short labels for search and rough grouping.
* Pricing: input, output, cache, per-call, or dynamic pricing.

## Model names

Use the exact model name shown in Model Square for the `model` field. Names can be case-sensitive and may include punctuation, slashes, or hyphens.

## API snippets

API snippets in Model Square are general request templates for OpenAI, Anthropic, or Google-compatible calls. They do not mean that every model has a unique API style.

When using a snippet, focus on three things:

| Field             | What to check                                                                                    |
| ----------------- | ------------------------------------------------------------------------------------------------ |
| Protocol          | Choose the OpenAI, Anthropic, or Google-compatible request shape for your client                 |
| Model name        | Replace `model` with the exact model name copied from Model Square                               |
| Parameter support | Different models support different parameters; unsupported parameters may be ignored or rejected |

For your first external call, use the direct HTTP or SDK examples in [Quickstart](/en/overview/quickstart).

## Tokens and prices

Tokenization depends on the model. Chinese, English, punctuation, code, JSON, and whitespace can produce different token counts. Actual usage is reported in API `usage` fields and Usage logs.

Common pricing types:

| Type           | Meaning                                                  |
| -------------- | -------------------------------------------------------- |
| Input price    | Request messages, system prompts, and document context   |
| Output price   | Tokens generated by the model                            |
| Cache price    | Prompt cache read or write pricing                       |
| Per-call price | Fixed price for some image, task, or tool calls          |
| Dynamic price  | Pricing calculated from request parameters or tier rules |

For token-based models:

```text theme={null}
cost = input tokens x input price + output tokens x output price
```

Prices are usually displayed per million tokens. Dynamic pricing and task-based pricing should be confirmed from the page pricing notes and final Usage logs.

## Selection guidance

* Basic classification, summarization, and formatting: start with lower-cost fast models.
* Reasoning, coding, and long analysis: choose stronger reasoning or context models.
* Image understanding: do not rely on tags alone; upload a sample in Conversation to confirm image input support.
* Document QA: check context length, PDF support, and pricing.
* Structured data: choose models that support JSON mode or tool calls reliably.

## Cost controls

* Keep only necessary conversation history and context.
* Set `max_tokens` when output length should be bounded.
* Use prompt caching when a model supports repeated prefixes.
* Create separate API keys with quota limits per project.
* Review high-cost calls in Usage.

## Next steps

* [Billing](/en/platform/billing)
* [Dashboard and usage](/en/platform/dashboard-and-usage)
* [Conversation](/en/platform/playground)