inclusionAI: Ling-2.6-flash
Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and high token efficiency....
Everything else
| Max output | 33K |
|---|---|
| Input / 1M | $0.01 |
| Output / 1M | $0.03 |
| Cache read / 1M | $0.002 |
| Cache write / 1M | — |
| 1M in + 1M out | $0.04 |
| Takes | text |
| Returns | text |
| Tools | yes |
| Reasoning | no |
| Open weights | no |
| Released | 2026-04-21 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | inclusionai/ling-2.6-flash |
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.