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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrafp8 | $0.070 | $0.340 | 262K | 99.7% |
| Cloudflare | $0.100 | $0.300 | 256K | 99.8% |
| SiliconFlowfp8 | $0.120 | $0.400 | 262K | 100% |
| Novitabf16 | $0.130 | $0.400 | 262K | 99.8% |
| Ionstreambf16 | $0.130 | $0.400 | 262K | 97.8% |
| Parasailbf16 | $0.130 | $0.400 | 262K | 99.4% |
| Venicebf16 | $0.130 | $0.400 | 256K | 99.2% |
| $0.150 | $0.600 | 262K | 97.4% | |
| NextBitbf16 | $0.180 | $0.500 | 262K | 99.9% |
Gemma 4 26B A4B costs $0.070 per million input tokens and $0.340 per million output tokens via OpenRouter, making it 30th cheapest of 332 paid models.
Gemma 4 26B A4B supports a 262K-token context window and can output up to 16K tokens. It accepts image, text, video input.