Gemma 4 26B A4B

💬 Chat & Text Google google/gemma-4-26b-a4b-it ⧉ Input 6.30 · Output 21 credits per 1M tokens
💬

Sign in to try Gemma 4 26B A4B

Sign in with your Google account and top up credits to get started.

Sign in with Google

Use via API

Base URL: https://adverraai.com/hub/api/v1 · Authenticate with Authorization: Bearer YOUR_API_KEY — create a key in your dashboard

curl https://adverraai.com/hub/api/v1/chat/completions \
  -H "Authorization: Bearer $ADVERRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-26b-a4b-it",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": false
  }'

Fully compatible with OpenAI Chat Completions: stream, temperature, max_tokens, tools, image messages, etc. The response includes usage.credits showing the credits used.

Parameters for this model

Send as JSON in the request body. Fields marked * are required.

ParameterTypeAllowed valuesDefaultDescription
model * string – – ID of the model to call — google/gemma-4-26b-a4b-it
messages * array – – Conversation messages, each with role (system / user / assistant) and content
max_tokens integer – – Maximum tokens in the answer
temperature number 0 – 2 1 Randomness of the answer; lower is steadier
top_p number 0 – 1 1 Nucleus sampling threshold
stream boolean true, false false Stream the answer back in chunks (SSE)
stop string | array – – Sequences where generation stops
tools array – – Tools (functions) the model may call
tool_choice string | object – – Controls how tools are chosen
response_format object – – Forces an answer format such as JSON

About this model

Gemma 4 26B A4B is a Chat & Text model by Google

Input📝 Text🖼️ Image🎬 Video
PriceInput 6.30 · Output 21 credits per 1M tokens

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...

Preparing details in English…