inferious
Open-weight inference, routed through OpenRouter. Self-hosted on rented GPUs, batched for low cost and low latency.
Models
| Model | Context | In | Out | Input price | Output price |
|---|---|---|---|---|---|
| Example 8B (placeholder — replaced at GPU provisioning)example-model-8b | 32,768 | text | text | $50000.00/M | $150000.00/M |