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...
22 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
33 providers
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
9 providers
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
8 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it | Google |
26.1 | 131.072K | $0.042 | $0.22 | 2026-04-02 | ||
| Google: Gemma 4 31Bgoogle/gemma-4-31b-it | Google |
15.4 | 262.144K | $0.09 | $0.34 | 2026-04-02 | ||
| Google: Gemma 3 27Bgoogle/gemma-3-27b-it | Google |
4.9 | 131.072K | $0.08 | $0.45 | 2025-03-12 | ||
| Google: Gemma 3 12Bgoogle/gemma-3-12b-it | Google |
3.8 | 131.072K | $0.05 | $0.15 | 2025-03-12 |