AI Observatory / Model Radar
Google / google/gemma-4-26b-a4b-it:free
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...
262,144
Context
32,768
Max output
<$0.01 / 1M
Prompt price
2026-04-03
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Input modalities | image, text, video | |
|---|---|---|---|
| Output modalities | text | Prompt price | <$0.01 / 1M |
| Completion price | <$0.01 / 1M | Request price | N/A |
| Context length | 262,144 | Max completion tokens | 32,768 |
| Supported parameters | include_reasoning, max_tokens, reasoning, response_format, seed, temperature, tool_choice, tools, top_p | ||
Best for
google/gemma-4-26b-a4b-it:free
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...
Cross-modal work
Long context
High-volume usage
Coding workflows
new
vision
tool-capable
long-context
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.