Google: Gemma 4 26B A4B
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...
Modalities
In / Out Price
$0.09 / $0.30 per 1M
Context
262K
Released
Apr 3, 2026
Knowledge Cutoff
—
Pricing
What Reroute charges per unit. No markup on inference — you pay the carrier's price, metered from the carrier's own usage numbers.
Input tokens
$0.09 / M
Output tokens
$0.30 / M
Cache read
$0.05 / M
By provider
Each carrier sets its own price. The router weighs these against uptime when it picks one.
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Discount |
|---|---|---|---|---|---|
 Darkbloom | $0.042 | $0.22 | $0.021 | — | — |
 Io Net | $0.0517 | $0.225 | $0.0217 | — | 25% |
 DekaLLM | $0.06 | $0.33 | $0.04 | — | — |
 DeepInfra | $0.07 | $0.34 | — | — | — |
 Makora | $0.08 | $0.32 | $0.032 | — | — |
 NextBit | $0.09 | $0.30 | $0.05 | — | — |
 CoreWeave | $0.10 | $0.30 | $0.05 | — | — |
 Cloudflare | $0.10 | $0.30 | $0.05 | — | — |
 Venice | $0.13 | $0.40 | $0.05 | — | — |
 Parasail | $0.13 | $0.40 | $0.05 | — | — |
 Novita | $0.13 | $0.40 | — | — | — |
 SiliconFlow | $0.14 | $0.40 | $0.05 | — | — |
 Google | $0.15 | $0.60 | — | — | — |