> 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 full documentation content in one file, see https://docs.sarvam.ai/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server.

# Migrating from Gemini: Overview

> Common setup changes for teams moving from the Gemini API to Sarvam: base URL, auth header, SDK client, and error handling, shared across every guide in this section.

*Last updated: July 15, 2026*

This page covers the setup changes that stay the same no matter which of your existing Gemini integrations you're moving over: base URL, auth header, and SDK client. Each product-specific migration guide already includes these same changes inline, so you don't need to read this page first; it's here as a standalone reference if you want the setup changes on their own.

## Quick start

Swap the client, then keep the rest of your code as-is:

#### Before (Gemini)

```python
from google import genai

client = genai.Client(api_key="YOUR_GEMINI_API_KEY")
```

#### After (Sarvam)

```python
from sarvamai import SarvamAI

client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
```

Both SDKs are also available for TypeScript/JavaScript; see [SDKs & Libraries](/api/getting-started/sdks) for install instructions and language coverage.

For requests made directly over HTTP rather than through an SDK, the only change is the header and base URL:

#### Before (Gemini)

```bash
curl -X POST "https://generativelanguage.googleapis.com/..." \
  -H "x-goog-api-key: YOUR_GEMINI_API_KEY"
```

#### After (Sarvam)

```bash
curl -X POST https://api.sarvam.ai/... \
  -H "api-subscription-key: YOUR_SARVAM_API_KEY"
```

> **Note**
>
> If your Gemini integration goes through the `openai` Python package pointed at Gemini's OpenAI-compatible endpoint rather than the native `google-genai` SDK, see the base URL and auth swap for that specific path in the [Chat Completion guide](/api/migrations/from-gemini/chat-completion): Sarvam's Chat Completions endpoint is OpenAI-compatible too, so that migration can be a two-line change.

## Base URL and auth

|                     | Gemini API                                  | Sarvam                            |
| ------------------- | ------------------------------------------- | --------------------------------- |
| Base URL            | `https://generativelanguage.googleapis.com` | `https://api.sarvam.ai`           |
| Auth header         | `x-goog-api-key: <api_key>`                 | `api-subscription-key: <api_key>` |
| Auth failure status | `401`                                       | `403`                             |

## Errors and rate limits

Sarvam returns `403` (not `401`) on authentication failures, and rate limits are enforced per API rather than account-wide. See [Errors & Troubleshooting](/api/getting-started/errors-troubleshooting) and [Credits & Rate Limits](/api/getting-started/ratelimits) for status codes and retry behavior. These apply the same way across every migration guide in this section.

## See also

* [Migrating Chat Completion](/api/migrations/from-gemini/chat-completion)
* [Migrating Text-to-Speech](/api/migrations/from-gemini/text-to-speech)
* [Migrating Speech-to-Text](/api/migrations/from-gemini/speech-to-text)
* [SDKs & Libraries](/api/getting-started/sdks)
* [Errors & Troubleshooting](/api/getting-started/errors-troubleshooting)

> Common setup changes for teams moving from the Gemini API to Sarvam: base URL, auth header, SDK client, and error handling, shared across every guide in this section.