🇨🇳 China
| Model | Intelligence | tok/s | $/M in | $/M out | $ / session | Cache |
|---|---|---|---|---|---|---|
| Ling-3.0-flash | 20.1 | 354.3 | $0.02 | $0.06 | — | — |
| Ling-3.0-flash-VL | 24.6 | — | $0.02 | $0.06 | — | — |
| Ling-3.0-flash-Fin | 22.6 | 354.9 | $0.04 | $0.12 | — | — |
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 |
|---|---|---|---|---|---|
| Ling-3.0-flash | Novita | unknown | $0.02 | $0.06 | 100.0% |
| Ling-3.0-flash | DeepInfra | bf16 | $0.06 | $0.18 | 97.3% |
| Ling-3.0-flash-VL | Novita | bf16 | $0.02 | $0.06 | 96.7% |
| Ling-3.0-flash-VL | DeepInfra | fp16 | $0.06 | $0.18 | 99.9% |
| Ling-3.0-flash-Fin | Novita | unknown | $0.04 | $0.12 | 100.0% |
| Ling-3.0-flash-Fin | DeepInfra | fp4 | $0.06 | $0.18 | 100.0% |