Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.oxen.ai/llms.txt

Use this file to discover all available pages before exploring further.

Try Gemma 4 31B in the Workbench

Run this model interactively, tune parameters, and compare outputs.
Model ID: gemma-4-31b-it Gemma 4 31B is the flagship dense multimodal model in the Gemma 4 family with 31 billion parameters. It supports text, image, and video inputs with a 256K token context window and over 140 languages. As the largest and most capable Gemma 4 variant, it achieves an estimated LMArena score of 1452, comparable to much larger models. Gemma 4 introduces Per-Layer Embeddings (PLE) for richer token representations, shared KV cache for efficient long-context inference, and variable aspect ratio vision encoding.
MetricValue
Parameter Count31 billion
Mixture of ExpertsNo
Context Length256,000 tokens
MultilingualYes (140+ langs)
Quantized*No
*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.

​
Example request

Use the Workbench as a request builder: configure parameters for this model in the UI, then open the API tab to copy the exact cURL or Python call.
curl -X POST https://hub.oxen.ai/api/ai/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "gemma-4-31b-it",
  "messages": [
    {
      "role": "user",
      "content": "Hello, what can you do?"
    }
  ]
}'

​
Fetch model details

The models endpoint returns the full model object, including its json_request_schema. 
curl -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/ai/models/gemma-4-31b-it

​
Request parameters

This model follows the standard OpenAI chat completions request body. See the chat completions reference for the full parameter list.