modeldock

Deploy Granite 3.3 8B Instruct as an OpenAI-compatible API

ModelDock launches Hugging Face models behind an OpenAI-compatible API. Granite 3.3 8B Instruct (enterprise-friendly open model under apache 2.0) is a 8.2B-parameter model from IBM, released under the apache-2.0 license. Paste its link in the dashboard and Pilot deploys it as a free 15-minute test, then you call it with any OpenAI SDK.

Granite 3.3 8B Instruct at a glance

Hugging Face repoibm-granite/granite-3.3-8b-instruct
Made byIBM
Parameters8.2B
Licenseapache-2.0
Context length (config.json)131,072 tokens
Hugging Face downloads69K (as of 2026-10-25)
Typical GPU24 GB: L4 / RTX A5000 / RTX 4090
Output price per 1M tokens$1.44 – $2.29
Input price per 1M tokens$0.36 – $0.57
Start fee$0.025 – $0.040

// facts from the Hugging Face model page. GPU tier and prices are Pilot’s typical pick for 16-bit weights using the pricing formula, not a guarantee; Pilot makes the final choice at launch, and paid launches are opening soon.

Launch it in three steps

  1. Sign in with your litepod account and paste https://huggingface.co/ibm-granite/granite-3.3-8b-instruct in the dashboard.
  2. Pilot checks the model, picks a GPU and deploys it. Copy the model id and an API key when it is ready.
  3. Call it with the code below. The free test lasts 15 minutes or 25 requests.
Python (openai)
from openai import OpenAI

client = OpenAI(base_url="https://api.lab.litepod.io/v1", api_key="sk_modeldock_...")

reply = client.chat.completions.create(
    model="modeldock/<your-model-id>",  # shown in the dashboard after launching ibm-granite/granite-3.3-8b-instruct
    messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)

More in the quickstart, OpenAI compatibility and limits. See pricing for every GPU tier.

Similar models

All models · More from litepod: the free LLM API with free open-source models