*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.
Prices for the AI credit you buy. $BINF holders pay up to 8% less.
| Charge | Price | Holders | Per |
|---|---|---|---|
| Inputper 1M tokens | $0.017 | $0.015 | per 1M tokens |
| Outputper 1M tokens | $0.050 | $0.046 | per 1M tokens |
| Cached inputper 1M tokens | $0.0034 | $0.0031 | per 1M tokens |
The price per million tokens, by day.
Unchanged since Sep 29, 2026: $0.017 in and $0.050 out per million tokens.
Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.
| Day | Input | Output | Reasoning | Calls |
|---|---|---|---|---|
| Oct 17 | 1,339,354,233 | 0 | 398,460 | 5,952 |
| Oct 18 | 742,810,547 | 0 | 220,952 | 3,303 |
The hosts serving this model now, and how often each answered over the last day.
Two settings: our address and your agent’s key. The model is set in each call.
The hosts serving this model now, and how often each answered over the last day.
| Host | Answered, last day | Context |
|---|---|---|
| Novita, answering | 100% | 262K |
| DeepInfraBf16bf16, answering | 91.6% | 131K |