Google: Gemma 4 26B A4B (free)
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Pricing
Source-reported prices are shown in their native units. No missing fee is estimated.
Input
Free
USD / 1M input tokens
Output
Free
USD / 1M output tokens
Capabilities
A check means the source explicitly lists support; a dash means the source did not publish a value.
Text input Supported
Text output Supported
Vision Supported
Tools Supported
Reasoning Supported
Structured outputs Supported
Audio Not listed
Image generation Not listed
Embeddings Not listed
Alternatives
Suggestions use deterministic rules: overlapping modalities, a context window within 2×, and shared source-reported signals. No AI-generated recommendations.
Similar models
Cohere: North Mini Code (free)
cohere/north-mini-code:free
Input
Free
Intelligence
9.9
Similar category, context, price or shared benchmark signals.
Dots Studio: Dots3-Note Preview (free)
dots-studio/dots-3-note-preview:free
Input
Free
Intelligence
N/A
Similar category, context, price or shared benchmark signals.
Free Models Router
openrouter/free
Input
Free
Intelligence
N/A
Similar category, context, price or shared benchmark signals.
Google: Gemma 4 31B (free)
google/gemma-4-31b-it:free
Input
Free
Intelligence
N/A
Similar category, context, price or shared benchmark signals.