Gemma 4 26B A4B
Liveby Google
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...
At a glance
AI chat API by Google, callable through Superpowers. It costs $0.09 in · $0.3 out per million tokens. Call it with one API key: POST /v1/run with "tool": "openrouter.google-gemma-4-26b-a4b-it", or over MCP with run_tool. 385 other providers in this category take the same input and can be compared side by side.
Ask your agent
Say it in your own words. Your agent picks this tool, fills in the details and brings back the answer.
Use Gemma 4 26B A4B to summarize this contract in five bullet points.
Ask Gemma 4 26B A4B to draft a friendly reply to this customer email.
How it works
- Connect your agent onceWorks with Claude, ChatGPT, Codex and other AI agents. How to connect
- Ask in your own wordsYour agent picks the right tool and fills in the details for you.
- Pay only when it worksEach use comes out of your balance. If it fails, you aren't charged.
For developersTool id, API call and input schema
- Tool id
- Price per call
- $0.00026 / 1K in + 500 out
- Per 1M tokens
- $0.09 in · $0.3 out
Call it
Also over MCP asrun_toolcurl -X POST https://superpowers.tools/v1/run \
-H 'Authorization: Bearer $SP_KEY' \
-d '{"tool":"openrouter.google-gemma-4-26b-a4b-it","input":{"prompt":"Explain MCP in one sentence."},"idempotency_key":"example-request-1"}'Input
5 fields · all optional{
"type": "object",
"properties": {
"prompt": {
"type": "string"
},
"system": {
"type": "string"
},
"messages": {
"type": "array",
"description": "OpenAI-style messages; overrides prompt"
},
"max_tokens": {
"type": "integer",
"default": 1024
},
"temperature": {
"type": "number"
}
}
}