> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://openrouter.ai/docs/llms.txt.
> For full documentation content, see https://openrouter.ai/docs/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://openrouter.ai/docs/_mcp/server.

# CreateEmbeddingsUsage - Python SDK

The Python SDK and docs are currently in beta.
Report issues on [GitHub](https://github.com/OpenRouterTeam/python-sdk/issues).

Token usage statistics

## Fields

| Field                   | Type                                                                               | Required             | Description                                                                                                                                                                                                   | Example |
| ----------------------- | ---------------------------------------------------------------------------------- | -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
| `cost`                  | *Optional\[float]*                                                                 | :heavy\_minus\_sign: | Cost of the request in credits                                                                                                                                                                                | 0.0001  |
| `prompt_tokens`         | *int*                                                                              | :heavy\_check\_mark: | Number of tokens in the input                                                                                                                                                                                 | 8       |
| `prompt_tokens_details` | [Optional\[operations.PromptTokensDetails\]](../operations/prompttokensdetails.md) | :heavy\_minus\_sign: | Per-modality token breakdown. Only present when the input contains 2+ modalities (e.g. text + image) and the upstream provider returns modality-level usage data. Only non-zero modality counts are included. |         |
| `total_tokens`          | *int*                                                                              | :heavy\_check\_mark: | Total number of tokens used                                                                                                                                                                                   | 8       |