Head to head
GLM-5.2 vs Inkling
On a blended workload of one million input tokens and three million output tokens, Inkling is 1.1× cheaper than GLM-5.2.
| GLM-5.2 | Inkling | |
|---|---|---|
| Provider | Together AI | Together AI |
| Input / MTok | $1.4 | $1 |
| Output / MTok | $4.4 | $4.05 |
| Cache read / MTok | — | — |
| Context window | 262,144 | 524,288 |
| Blended 1M in + 3M out | $14.60 | $13.15 |
| Status | ga | ga |