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...
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.
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.
Photo: RDNE Stock project
Cached input reads $0.05 per 1M · weights on Hugging Face as google/gemma-4-26B-A4B-it
A higher intelligence index, best first, with the price it comes at.
Other models by the same vendor in the catalogue.
The catalogue prints input and output prices and what three typical monthly workloads cost on each.
