Using Gemma 4 26B A4B IT on Novita AI

Implementation guide · Gemma 4 · Google DeepMind

ServerlessOpen Source

Quick Start

1
Create an account at Novita AI and generate an API key.
2
Use the Novita AI SDK or REST API to call gemma-4-26b-a4b-it.
3
You'll be billed $0.13/1M input, $0.40/1M output tokens. See full pricing.

Code Examples

Code examples for this provider have not been sourced yet.

About Novita AI

Novita AI offers a GPU-based inference API for image, video, and language model generation with a broad catalog of open-source models.

View all models on Novita AI →

Pricing on Novita AI

Type	Price (per 1M)
Input tokens	$0.13
Output tokens	$0.40

Capabilities

MultimodalFunction CallingStructured Outputs

About Gemma 4 26B A4B IT

Instruction-tuned MoE variant with 26B parameters (4B active). Optimized for instruction-following with advanced reasoning and multimodal capabilities.

Full model details →

Model Specs

Released2026-03-31

Parameters26B

Context256k

Knowledge cutoff2025-01