Gemma 1.1 7B Instruct on DeepInfra

Gemma · Google DeepMind

ServerlessOpen Weights

Last refreshed 2026-06-15. Next refresh: weekly.

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.

Input / 1M
$0.050
Output / 1M
$0.15
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install openai
Auth
export DEEPINFRA_API_KEY=...
Call
import os
from openai import OpenAI
client = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
Model ID
gemma-1.1-7b

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)

Gotchas

  • DeepInfra uses "organization/model-name" format, e.g. "meta-llama/Meta-Llama-3-8B-Instruct" or "mistralai/Mistral-7B-Instruct-v0.3". See the DeepInfra model catalog for exact IDs.
  • The examples expect DEEPINFRA_API_KEY; rename it only if your application config maps the new variable.

Pricing

TypePrice (per 1M)
Input tokens$0.05
Output tokens$0.15

Capabilities

Structured Outputs

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.

Get Started

Model Specs

Released2024-02-21
Parameters7B
Context8k
ArchitectureDecoder Only
Knowledge cutoff2023-04