Llama 3.1 8B CS-3 Hyper
Activecerebras/llama-3.1-8bInput / Prompt$0.00 / M
Output / Completion$0.00 / M
Context Window8K
Throughput Speed2,600 tps
3 Providers Serving This ModelDeterministic Failover Active
| Provider | Input /M | Output /M | Latency (TTFT) | Speed (TPS) | Uptime | Quantization | ZDR | Action |
|---|---|---|---|---|---|---|---|---|
CEREBRASPrimary Upstream | $0.00 / M | $0.00 / M | 0.12s | 2,600 tps | 99.98% | FP16 | No | Connect / Configure Provider → |
OpenRouter (Edge Router)Multi-Region Backup | $0.00 / M | $0.00 / M | 0.24s | 110 tps | 99.92% | FP8 | Yes | Connect / Configure Provider → |
Cerebras Cloud LPUInference Accelerator | $0.00 / M | $0.00 / M | 0.04s | 2,100 tps | 99.85% | INT8 | No | Connect / Configure Provider → |