Compare
Granite 4.0 Micro vs …
Put models side by side on context, price, speed and availability.
| Model | |
|---|---|
| Overview | |
| Developer | IBM |
| Context tokens | 128K |
| Max output tokens | 115K |
| Input | |
| Output | |
| Providers | 1 |
| Released | Oct 20, 2025 |
| Pricing | |
| Input per 1M | $0.02 |
| Output per 1M | $0.11 |
| Cache read per 1M | Variable |
| Performance | |
| Latency p50, median provider | 0.55s |
| Throughput p50, median provider | 34 tps |
| Uptime last 24h | 100.00% |
