Gemma 4 26B A4B - Free MoE Model on OpenRouter, 262K Context
Gemma 4 26B A4B - Free MoE Model on OpenRouter, 262K Context
Gemma 4 26B A4B is completely free: $0/M input tokens, $0/M output tokens.
Model Information
| Attribute | Value |
|---|---|
| Context length | 262,144 tokens |
| Max output | 32,768 tokens |
| Input price | $0 / 1M tokens |
| Output price | $0 / 1M tokens |
| Provider | |
| Status | Free |
Description
Gemma 4 26B A4B IT is a Mixture-of-Experts model from Google DeepMind. Although it has 25.2B total parameters, it activates only 3.8B per inference, delivering quality close to 31B.
Usage Example
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemma-4-26b-a4b-it:free",
"messages": [{"role": "user", "content": "Hello!"}]
}'Related Links
📚 Related Free Models
These models are also available for $0 on OpenRouter. Choose by context length and modality.
| Model | Context | Description |
|---|---|---|
| Ling 3.2 Flash | 1M | Ling 3.2 Flash is inclusionAI’s hybrid reasoning model |
| Particle-1 | 1M | Particle-1 is Particle AI’s agentic coding model, |
| ERNIE 5.5 Flash | 1M | Baidu’s ERNIE 5.5 Flash Preview free model has 280B |
| LFM3 1.7B | 262K | Liquid AI’s compact 1.7B text model with 262K context, |
| Recursive Flint | 262K | Recursive’s 40B total / 2.5B active MoE model built for |
| Dots3 Note | 512K | Dots3-Note Preview is Dots Studio’s MoE model with 280B |
| Gemma 4 31B - Free Multimodal Model on | 262K | Gemma 4 31B is Google DeepMind’s 30.7B dense multimodal |
| Lyria 3 Clip | 1M | Google’s music clip generation model produces 30-second |
📋 View all OpenRouter free models →
🔗 Site Navigation
Last updated on
· Source: OpenRouter official documentation and pricing pages. Quotas and prices may change at any time.