LLM Perks

DiffusionGemma 26B

Google DeepMind · All Gemma models
Free right now Mid-size
Tool useLong contextOpen weights

DiffusionGemma 26B is a language model with 26B parameters from Google DeepMind. It is currently free at 1 provider with up to 262K tokens of context. The model supports tool calling. Its weights are open, so it can also run locally.

Developer
Google DeepMind
Parameters
26B / 4B active
Context
262K tokens
Type
Text
License
Open weights

Where to use DiffusionGemma 26B for free

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

ProviderContextLimitCard
UnoRouter
diffusiongemma-26b-a4b-it:free
262K 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": "diffusiongemma-26b-a4b-it:free",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

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

Benchmarks

Intelligence Index
9.5
GPQA Diamond
66.9%
Humanity's Last Exam
10.8%
Long context (LCR)
19.7%

Source: Artificial Analysis · DiffusionGemma 26B A4B

Similar free models

FAQ

Is DiffusionGemma 26B free?

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

What is the context window of DiffusionGemma 26B?

The largest context among free routes is 262,144 tokens. Some providers cap it lower.

How do I call DiffusionGemma 26B via API?

Use any OpenAI-compatible client with base URL https://api.unorouter.com/v1, model ID diffusiongemma-26b-a4b-it:free, and a UnoRouter key.

How good is DiffusionGemma 26B?

Artificial Analysis Intelligence Index: 9.5, GPQA Diamond: 67%. For comparison, the strongest free model in the catalog right now is GLM 5.3.

Is DiffusionGemma 26B open-weight?

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