diffusiongemma-26b-a4b-it

google/diffusiongemma-26b-a4b-it

NVIDIA Build Card

Diffusion-based 26B parameter LLM enabling parallel token generation for real-time text apps

Context Length

262,144 tokens

Input Pricing

$0.18 / 1M

Output Pricing

$0.18 / 1M

Recent Latency

No probes

Model Architecture & Limits

Canonical IDgoogle/diffusiongemma-26b-a4b-it

Publisher / Originatorgoogle

Model FamilyGemma

ArchitectureTransformer (Mixture-of-Experts)

Context Window Limit262,144 tokens

Max Output Tokens4,096 tokens

Endpoint Protocolopenai-chat

Capabilities & Modal Surfaces

Chat Conversation✕ No

Tool / Function Calling✕ No

Reasoning / Thinking✕ No

Structured Output (JSON)✕ No

Vision / Multimodal✓ Yes

Audio Processing✕ No

License & Restrictions

**GOVERNING TERMS:** The trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of the model is governed by the [NVIDIA Open Model Agreement](https://www.nvidia.com/en-us/agre

Commercial and research use permitted under governing model and API terms.