Put models side by side on context, price, speed and availability.
| Model | |
|---|---|
| Overview | |
| Developer | Perceptron |
| Context tokens | 32K |
| Max output tokens | 8K |
| Input | |
| Output | |
| Providers | 1 |
| Released | May 12, 2026 |
| Pricing | |
| Input per 1M | $0.15 |
| Output per 1M | $1.50 |
| Cache read per 1M | Variable |
| Performance | |
| Latency p50, median provider | 2.21s |
| Throughput p50, median provider | 8 tps |
| Uptime last 24h | 100.00% |