LLM Perks

Gemma 4 31B

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

Gemma 4 31B is a language model with 31B parameters from Google DeepMind. It is currently free at 4 providers with up to 262K tokens of context. The model understands images, supports tool calling. Its weights are open, so it can also run locally.

Developer
Google DeepMind
Parameters
31B
Context
262K tokens
Type
Text
License
Open weights
Free since
September 19, 2026

Where to use Gemma 4 31B for free

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

ProviderContextLimitCard
OpenRouter
google/gemma-4-31b-it:free
262K Free tier No Open
Together AI
google/gemma-4-31B-it-lora
262K Fair use (depends on server load) — Open
NVIDIA Build
google/gemma-4-31b-it
— Free serverless inference for development; limits and model availability may change. No Open
UnoRouter
gemma-4-31b-it:free
262K No-card free models use shared capacity and per-model limits; availability can change. No Open

Quick start

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-31b-it:free",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

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

Benchmarks

Intelligence Index
19.0
GPQA Diamond
85.7%
Humanity's Last Exam
23.6%
Terminal-Bench Hard
36.4%
τ²-Bench
59.9%
Long context (LCR)
69.7%

Source: Artificial Analysis · Gemma 4 31B (Reasoning)

Similar free models

FAQ

Is Gemma 4 31B free?

Yes. As of September 26, 2026, Gemma 4 31B is free at OpenRouter, Together AI, NVIDIA Build, UnoRouter. Each provider has its own limits — see the table above.

What is the context window of Gemma 4 31B?

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

How do I call Gemma 4 31B via API?

Use any OpenAI-compatible client with base URL https://openrouter.ai/api/v1, model ID google/gemma-4-31b-it:free, and a OpenRouter key.

How good is Gemma 4 31B?

Artificial Analysis Intelligence Index: 19.0, GPQA Diamond: 86%. For comparison, the strongest free model in the catalog right now is GLM 5.3.

Is Gemma 4 31B open-weight?

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