google-deepmind/gemma-3-27b-it:c0f0aebe – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

google-deepmind /gemma-3-27b-it:c0f0aebe

Playground API

Input

Run this model in Node.js with one line of code:

npx create-replicate --model=google-deepmind/gemma-3-27b-it

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run google-deepmind/gemma-3-27b-it using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "google-deepmind/gemma-3-27b-it:c0f0aebe8e578c15a7531e08a62cf01206f5870e9d0a67804b8152822db58c54",
  {
    input: {
      top_k: 50,
      top_p: 0.9,
      prompt: "What is the speed of an unladen swallow?",
      temperature: 0.7,
      system_prompt: "You are a helpful assistant.",
      max_new_tokens: 512
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run google-deepmind/gemma-3-27b-it using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "google-deepmind/gemma-3-27b-it:c0f0aebe8e578c15a7531e08a62cf01206f5870e9d0a67804b8152822db58c54",
    input={
        "top_k": 50,
        "top_p": 0.9,
        "prompt": "What is the speed of an unladen swallow?",
        "temperature": 0.7,
        "system_prompt": "You are a helpful assistant.",
        "max_new_tokens": 512
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run google-deepmind/gemma-3-27b-it using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "google-deepmind/gemma-3-27b-it:c0f0aebe8e578c15a7531e08a62cf01206f5870e9d0a67804b8152822db58c54",
    "input": {
      "top_k": 50,
      "top_p": 0.9,
      "prompt": "What is the speed of an unladen swallow?",
      "temperature": 0.7,
      "system_prompt": "You are a helpful assistant.",
      "max_new_tokens": 512
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Ah, a classic question! As famously debated in *Monty Python and the Holy Grail*, determining the speed of an unladen swallow is... complicated. Here's the breakdown: * **European Swallow:** Approximately 11 meters per second, or 24 miles per hour. * **African Swallow:** This is where it gets tricky! There's no definitive answer given in the film, and it's a point of contention. It's implied the African swallow is *faster*, but by how much is unknown. Some estimations, based on ornithological data, put it around 25-30 mph, but it's largely left as a humorous mystery. **The key point from the movie is that you *must* specify which kind of swallow you're talking about!** So, to give you the most accurate answer: **An unladen European Swallow travels at roughly 24 mph.** <end_of_turn>

Generated in

15.0 seconds

Tweak it Share Report