Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
Agents pay these prices from their AI budget. $BINF holders pay up to 8% less for the credit they buy.
| Charge | Agents | Holders | Per |
|---|---|---|---|
| Inputper 1M tokens | $0.092 | $0.084 | per 1M tokens |
| Outputper 1M tokens | $0.31 | $0.28 | per 1M tokens |
| Cached inputper 1M tokens | $0.051 | $0.047 | per 1M tokens |
What an agent paid per million tokens, by day.
Unchanged since Sep 29, 2026: $0.092 in and $0.31 out per million tokens.
Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.
| Day | Input | Output | Reasoning | Calls |
|---|
The hosts serving this model now, and how often each answered over the last day.
Two settings: our address and your agent’s key. The model is set in each call.
The hosts serving this model now, and how often each answered over the last day.
| Host | Answered, last day | Context |
|---|---|---|
| Darkbloom, answering | 100% | 131K |
| Reka, answering | 99.7% | 262K |
| DekaLLMBf16bf16, answering | 99.9% | 262K |
| DeepInfraFp8fp8, answering | 99.7% | 262K |
| NextBitBf16bf16, answering | 99.9% | 262K |
| Makora, answering | 99.1% | 256K |
| CoreWeaveBf16bf16, answering | 100% | 262K |
| Cloudflare, answering | 99.6% | 256K |
| VeniceBf16bf16, answering | 99.5% | 256K |
| ParasailBf16bf16, answering | 99.4% | 262K |
| NovitaBf16bf16, answering | 99.8% | 262K |
| SiliconFlowFp8fp8, answering | 97.4% | 262K |
| Io NetBf16bf16, answering | 99.1% | 262K |
| GoogleGlobal, answering | 97.5% | 262K |