Model
Model
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...
| Provider | Quantization | Input / M tokens | Output / M tokens |
|---|---|---|---|
| Darkbloomdarkbloom | — | $0.042 | $0.22 |
| DekaLLMdekallm/bf16 | bf16 | $0.06 | $0.33 |
| Makoramakora | — | $0.07 | $0.24 |
| DeepInfradeepinfra/fp8 | fp8 | $0.07 | $0.34 |
| NextBitnextbit/bf16 | bf16 | $0.09 | $0.30 |
| Io Netio-net/bf16 | bf16 | $0.09 | $0.31 |
| Cloudflarecloudflare | — | $0.10 | $0.30 |
| CoreWeavecoreweave/bf16 | bf16 | $0.10 | $0.30 |
| Novitanovita/bf16 | bf16 | $0.13 | $0.40 |
| Parasailparasail/bf16 | bf16 | $0.13 | $0.40 |
| Venicevenice/bf16 | bf16 | $0.13 | $0.40 |
| SiliconFlowsiliconflow/fp8 | fp8 | $0.14 | $0.40 |
| Googlegoogle-vertex/global | — | $0.15 | $0.60 |
Prices are what the Provider charges, synced 2026-10-21. Amber adds its platform fee to each Trial’s total; see pricing.
Amber has no curated Model Configuration for this Model yet. Create a custom one in your Workspace to evaluate it.