LLM Perks

Granite 4.0 Micro

Free right now Small New
Open weights

Granite 4.0 Micro is a language model from IBM. It is currently free at 1 provider with up to 131K tokens of context. Its weights are open, so it can also run locally.

Developer
IBM
Context
131K tokens
Type
Text
License
Open weights
Free since
September 21, 2026

Where to use Granite 4.0 Micro for free

Each row is a separate free endpoint with its own limits.

ProviderContextLimitCard
UnoRouter
granite-4.0-micro:free
131K No-card free models use shared capacity and per-model limits; availability can change. No Open

Quick start

curl https://api.unorouter.com/v1/chat/completions \
  -H "Authorization: Bearer $UNOROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "granite-4.0-micro:free",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example for UnoRouter. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.

Benchmarks

Intelligence Index
5.1
GPQA Diamond
33.6%
Humanity's Last Exam
5.0%
Terminal-Bench Hard
1.5%
τ²-Bench
12.6%
Long context (LCR)
7.0%

Source: Artificial Analysis · Granite 4.0 Micro

Similar free models

FAQ

Is Granite 4.0 Micro free?

Yes. As of September 26, 2026, Granite 4.0 Micro is free at UnoRouter. Each provider has its own limits — see the table above.

What is the context window of Granite 4.0 Micro?

The largest context among free routes is 131,000 tokens. Some providers cap it lower.

How do I call Granite 4.0 Micro via API?

Use any OpenAI-compatible client with base URL https://api.unorouter.com/v1, model ID granite-4.0-micro:free, and a UnoRouter key.

How good is Granite 4.0 Micro?

Artificial Analysis Intelligence Index: 5.1, GPQA Diamond: 34%. For comparison, the strongest free model in the catalog right now is GLM 5.3.

Is Granite 4.0 Micro open-weight?

Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.