🇺🇸 United States
| Model | Coding index | tok/s | $/M in | $/M out | $ / session | Cache |
|---|---|---|---|---|---|---|
| Granite 4.1 8B | 9.5 | 128.6 | $0.05 | $0.10 | — | — |
Everyone serving these models, cheapest first, with the numeric precision each one runs. The lab is often not the cheapest place to buy its own model.
| Model | Served by | Quant | $/M in | $/M out | Uptime 30m |
|---|---|---|---|---|---|
| Granite 4.1 8B | CoreWeave | bf16 | $0.05 | $0.10 | 100.0% |