AI modelBase plan

Gemma 4 26B A4B

Google's open-weights Gemma 4 mixture-of-experts model (26B total, about 4B active) via the Vercel AI Gateway on Vertex AI and Parasail: quick, low-cost chat and image understanding with a 256k-token context window. Uses 1 base request per send before length multipliers. Supports image input. Web search runs through Perplexity.

The model you pick is the model that answers. Some replies follow our crisis protocol and may be fixed text.

Specifications

IntelligenceMedium
SpeedFast
Context window262,144 tokens
Max output131,072 tokens
Knowledge cutoffNot officially published
Input price$0.15 / 1M tokens
Output price$0.60 / 1M tokens
Request cost1 base request
Plan tierBase
InputText, Image
OutputText
FeaturesCached input: $0.015 / 1M tokens, 1 base request per send before length multipliers, Open weights, Function calling supported, Image input supported, Served through the Vercel AI Gateway (google/gemma-4-26b-a4b-it), Zero data retention and no prompt training
Model IDgemma-4-26b-a4b

Specifications and list prices are as published by the model's provider and can change. Request cost is what the model uses on just4o.chat.

Related models