Migrating Chat Completion from Gemini to Sarvam

This guide covers migrating Gemini text generation and chat calls to Sarvam. It doesn’t cover Gemini’s audio capabilities; see Migrating Text-to-Speech and Migrating Speech-to-Text for those.

Quick start

Base URL and auth header change the same way for every Gemini migration on the native SDK path, so they’re folded in here rather than in a separate page:

With that, replace the generation call:

1
from google import genai
2
3
client = genai.Client(api_key="YOUR_GEMINI_API_KEY")
4
5
interaction = client.interactions.create(
6
    model="gemini-3.5-flash",
7
    input="What's a good name for a coffee shop in Bengaluru?",
8
    system_instruction="You are a helpful assistant.",
9
    generation_config={
10
        "temperature": 0.7,
11
        "max_output_tokens": 200,
12
    },
13
)
14
15
print(interaction.output_text)

If your code goes through the openai package instead, see the next section: it’s a separate, often simpler route for Chat Completion specifically.

If you’re using the OpenAI-compatible endpoint

Gemini exposes an OpenAI-compatible Chat Completions endpoint, and so does Sarvam. If your code already goes through the openai package, migrating is just a client config change:

1
from openai import OpenAI
2
3
client = OpenAI(
4
    api_key="YOUR_GEMINI_API_KEY",
5
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/",
6
)
7
8
response = client.chat.completions.create(
9
    model="gemini-3.5-flash",
10
    messages=[
11
        {"role": "system", "content": "You are a helpful assistant."},
12
        {"role": "user", "content": "Hello!"},
13
    ],
14
)
15
16
print(response.choices[0].message.content)

Endpoint map

Parameter concept map

What’s different by design

• One message list, not a split input/system_instruction. The system prompt is just another entry in messages, so the whole conversation, including instructions, lives in one place.
• No interaction ID to track. Sarvam follows the stateless, resend-the-history convention used by OpenAI-compatible tooling broadly, rather than Gemini’s previous_interaction_id chaining; if your app already manages its own message history, it carries over as-is.
• A response shape you may already know. response.choices[0].message.content matches the OpenAI Chat Completions shape exactly, since Sarvam’s endpoint is OpenAI-compatible; there’s no separate native shape to learn if you’re coming from the OpenAI-compatible Gemini path.
• Hybrid thinking mode built into the model. sarvam-30b and sarvam-105b support both “think” and “non-think” modes via reasoning_effort, tuned for complex reasoning and coding without needing a separate reasoning-specific model.
• Advanced Indic skills are Sarvam’s specific strength. Both models are post-trained on Indian languages and cultural context, with native script and romanized-language support, alongside strong English performance.

Full example

A small wrapper function, before and after, showing the complete set of changes together:

1
from google import genai
2
3
client = genai.Client(api_key="YOUR_GEMINI_API_KEY")
4
5
def ask(prompt: str, system: str = "You are a helpful assistant.") -> str:
6
    interaction = client.interactions.create(
7
        model="gemini-3.5-flash",
8
        input=prompt,
9
        system_instruction=system,
10
    )
11
    return interaction.output_text

Common mistakes

See also

• Migration overview: base URL, auth, and SDK client changes
• Migrating Text-to-Speech
• Migrating Speech-to-Text
• Chat Completion Overview
• Authentication
• Errors & Troubleshooting