Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
google/gemma-4-26b-a4b-itCatalogue: Indexed in the reference catalogue; nothing on this deployment answers as this model yet.
Published by the vendor; the platform bills at the target's declared price.
Google google/gemma-4-26b-a4b-it
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...
Cached input reads $0.05 per 1M · weights on Hugging Face as google/gemma-4-26B-A4B-it
Gemma 4 26B A4B earns a request when it needs step-by-step reasoning, tool calls, very long inputs; a short, general request would go to Nemotron 3.5 Super VL (free) instead - free per million input tokens against $0.09 here; and the hardest requests, where the quality floor rules it out, to Claude Opus 5.5 (batch). Your rules decide the floor; the trace shows the comparison for every request.
Lower input price and an intelligence index within 5 points.
A higher intelligence index, best first, with the price it comes at.
Nothing on this deployment answers as this model yet. Connect your own provider under Model providers, or add a target to your catalogue - the router picks it up without retraining.
# targets.yaml - declare a target that runs Gemma 4 26B A4B
targets:
- id: gemma-4-26b-a4b-it
kind: llm
name: Gemma 4 26B A4B
metadata:
model: google/gemma-4-26b-a4b-it # links the target to this catalogue entry
capabilities:
domains: [general]
supports_tools: true
context_window: 262144
cost:
usd_per_1k_tokens: 0.000195Input list price per million tokens; Gemma 4 26B A4B is the cheapest of 13 listed.
Other models by the same vendor in the catalogue.
Photo: RDNE Stock project
