Gemma 4 31B

Gemma 4 31B is a 31B-parameter instruction-tuned model for text and image understanding. It accepts text and inline images with a 262,144-token context window. It answers directly by default and can reason first when you set reasoning_effort (see Reasoning).

At a glance

Key capabilities

Quickstart

The examples send a local image as a base64 data URI. Remote image URLs are not supported.

import base64
from sarvamai import SarvamAI
client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
with open("chart.png", "rb") as image:
    encoded = base64.b64encode(image.read()).decode("utf-8")
response = client.chat.completions_v2(
    model="gemma4",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What trend does this chart show?"},
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/png;base64,{encoded}"},
                },
            ],
        }
    ],
    temperature=1,
    top_p=0.95,
    max_tokens=500,
)
print(response.choices[0].message.content)

Reasoning

Gemma 4 answers directly by default. To have it reason before answering, set an effort level:

On chat, read the reasoning trace from choices[].message.reasoning_content. Reasoning tokens are billed as output tokens and count against max_tokens / max_output_tokens.

Supported parameters

model: "gemma4" on Chat Completion V2 and Responses. Full request/response schemas live on those API reference pages; this table covers what’s actually accepted for this model.

400 is invalid_request_error. Images must be base64 data URIs in image_url content parts (remote URLs are rejected).

Limits and errors