> This page is for Model APIs.

> Sarvam Voice Agents (Samvaad) is a voice AI agent platform for Indian languages: build, test and deploy AI calling agents on your own phone numbers, from ₹3 a minute. Start here: https://docs.sarvam.ai/voice-agents/why-voice-agents.
> For clean Markdown of any page, append `.md` to the page URL.
> For a complete documentation index, see https://docs.sarvam.ai/llms.txt. For a section index, append `/llms.txt` to any section URL (for example https://docs.sarvam.ai/voice-agents/llms.txt).
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server.

# Languages, Formats & Limits

> Languages, accepted input formats, page and file-size limits, and rate limits for the Document AI API.

## Supported Languages

Document AI supports all 22 Constitutionally recognized Indian languages plus English:

| Language  | Code     |
| --------- | -------- |
| Hindi     | `hi-IN`  |
| Bengali   | `bn-IN`  |
| Tamil     | `ta-IN`  |
| Telugu    | `te-IN`  |
| Marathi   | `mr-IN`  |
| Gujarati  | `gu-IN`  |
| Kannada   | `kn-IN`  |
| Malayalam | `ml-IN`  |
| Odia      | `od-IN`  |
| Punjabi   | `pa-IN`  |
| Assamese  | `as-IN`  |
| Bodo      | `brx-IN` |
| Dogri     | `doi-IN` |
| Kashmiri  | `ks-IN`  |
| Konkani   | `kok-IN` |
| Maithili  | `mai-IN` |
| Manipuri  | `mni-IN` |
| Nepali    | `ne-IN`  |
| Sanskrit  | `sa-IN`  |
| Santali   | `sat-IN` |
| Sindhi    | `sd-IN`  |
| Urdu      | `ur-IN`  |
| English   | `en-IN`  |

For the model behind these languages, see the [Sarvam Vision model page](/api/getting-started/models/sarvam-vision).

## Supported input formats

| Format | Extension       |            Parse and Extract           | Split and Classify |
| ------ | --------------- | :------------------------------------: | :----------------: |
| PDF    | `.pdf`          |                   Yes                  |         Yes        |
| PNG    | `.png`          |                   Yes                  |         Yes        |
| JPEG   | `.jpg`, `.jpeg` |                   Yes                  |         Yes        |
| TIFF   | `.tif`, `.tiff` |                   No                   |         Yes        |
| ZIP    | `.zip`          | Yes (flat archive of JPG or PNG pages) |         No         |

> **Note**
>
> For ZIP files, include only JPG and PNG document pages in a flat structure (no nested folders). The API processes all pages in the archive and maintains page order based on filename.

## Limits

| Limit          | Parse  | Extract | Split and Classify  |
| -------------- | ------ | ------- | ------------------- |
| Pages per PDF  | 30     | 20      | 500                 |
| Images per ZIP | 30     | 20      | Not supported       |
| File size      | 200 MB | 200 MB  | 512 MB per document |

Split and Classify also accept up to 10 documents per request, up to 20 categories, and up to 1,000 segments. Requests per minute vary by plan and operation. See [Document AI rate limits](/api/getting-started/ratelimits#document-ai).

> **Warning**
>
> **Page limit:** Exceeding a page or image limit returns a `400 Bad Request` with code `invalid_request_error`. [Split](/api/api-guides-tutorials/document-intelligence/how-to/split) larger documents into batches before uploading.