Gemma 4 26B A4B (free) pricing & benchmarks
Released Apr 3, 2026 · served by 2 providers
What Gemma 4 26B A4B (free) is
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...
- Model ID:
google/gemma-4-26b-a4b-it:free - Modality: text+image+video->text
- Tool calling: supported · Structured output: supported
- Weights:
google/gemma-4-26B-A4B-iton Hugging Face
Providers and prices for Gemma 4 26B A4B (free)
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| Darkbloomcheapest | Free | Free | 131K | — | 96.7% | — |
| Google AI Studio | Free | Free | 262K | — | 99.4% | — |
FAQ
How much does the Gemma 4 26B A4B (free) API cost?
Free per 1M input tokens and Free per 1M output tokens.
Is Gemma 4 26B A4B (free) free?
Yes — it is served at $0 for both input and output tokens on OpenRouter, subject to rate limits.
Which provider is cheapest for Gemma 4 26B A4B (free)?
Darkbloom at Free input / Free output per 1M tokens.
Can I self-host Gemma 4 26B A4B (free)?
Yes — weights are published as google/gemma-4-26B-A4B-it on Hugging Face, so you can run it on your own hardware.