Back to all models

Gemma 4 26B A4B IT

Gemma 4 26B mixture-of-experts instruction-tuned model (4B active) with reasoning.

gemma-4-26b-a4b-it
STABLEGet StartedView uptime
262,144 context
Released April 2, 2026
Starting at $0.07/M input tokens
Starting at $0.34/M output tokens
Streaming
Tools
Reasoning
JSON Output
No ratings yetSign in to rate

Select Provider

All Providers for Gemma 4 26B A4B IT

DigitSpace routes requests to the best providers that are able to handle your prompt size and parameters.

DeepInfra
Context: 262.1kQuant: fp8
Input
$0.07
/M tokens
Cache Read
—
/M tokens
Output
$0.34
/M tokens
Get Started
NovitaAI
Context: 262.1kQuant: bf16
Input
$0.13
/M tokens
Cache Read
—
/M tokens
Output
$0.4
/M tokens
Get Started

Frequently asked questions

What is Gemma 4 26B A4B IT?

Gemma 4 26B mixture-of-experts instruction-tuned model (4B active) with reasoning. You can access it through DigitSpace's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does Gemma 4 26B A4B IT cost?

Pricing for Gemma 4 26B A4B IT on DigitSpace starts at $0.07 per million input tokens and $0.34 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of Gemma 4 26B A4B IT?

Gemma 4 26B A4B IT supports a context window of up to 262,144 tokens on its largest provider deployment.

Which providers serve Gemma 4 26B A4B IT?

Gemma 4 26B A4B IT is served by DeepInfra, NovitaAI through DigitSpace. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does Gemma 4 26B A4B IT support tool calling and structured outputs?

Gemma 4 26B A4B IT supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).

When was Gemma 4 26B A4B IT released?

Gemma 4 26B A4B IT was released on April 2, 2026.