ibm-granite/granite-4.0-h-micro

$0.02

Input / 1M

$0.11

Output / 1M

131K

Context

—

Speed

Capabilities

No capabilities flagged in the catalog.

Use granite-4.0-h-micro via Relay

Configure the model alias in YAML, then call it from Python.

YAML

# models.yaml
version: 1
models:
  granite:
    target: ibm-granite/granite-4.0-h-micro
    credential: $env.IBM-GRANITE_API_KEY

Python

from relay import Hub

async with Hub.from_yaml("models.yaml") as hub:
    resp = await hub.chat(
        "granite",
        messages=[{"role": "user", "content": "Hello"}],
    )
    print(resp.text, resp.cost_usd)

pip install ai5labs-relay · full docs on GitHub

Compare with

vs groq/llama-3.3-70b-versatile vs anthropic/claude-haiku-4-5 vs mistral/mistral-large-latest vs openai/gpt-4o-mini