Gemma 1.1 7B Instruct on DeepInfra

Why use Gemma 1.1 7B Instruct on DeepInfra?

DeepInfra offers Gemma 1.1 7B Instruct with pay-as-you-go pricing at $0.05/1M input tokens. DeepInfra is a cloud inference platform offering cost-effective access to open-source AI models.

Request example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
    base_url="https://api.deepinfra.com/v1/openai"
)
response = client.chat.completions.create(
    model="gemma-1.1-7b",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Pricing

Capabilities

About Gemma 1.1 7B Instruct

The Gemma 1.1 7B Instruct model is a cutting-edge, lightweight large language model developed by Google. As a part of the Gemma model family, it benefits from the same foundational research and technological advancements as Google's Gemini models. Unique to this model is its instruction-tuned training, which allows it to follow directives with greater precision than its base variants. Despite its compact size of 7 billion parameters, making it suitable for deployment on resource-constrained devices like desktops, it excels in diverse tasks including question answering, summarization, logical reasoning, and coding assistance. The model employs a transformer-based, decoder-only architecture, trained on an extensive dataset with an innovative use of Reinforcement Learning from Human Feedback (RLHF) to enhance its quality, factuality, and conversational capabilities. It supports multiple precision levels and is openly available, promoting collaboration in the AI community. Nonetheless, it shares common LLM limitations like potential data biases and factual inaccuracies, which are addressed through guidelines for responsible use.

Get Started