Head to head
Inkling Small vs GPT-5.4 nano
On a blended workload of one million input tokens and three million output tokens, GPT-5.4 nano is 1.0× cheaper than Inkling Small.
| Inkling Small | GPT-5.4 nano | |
|---|---|---|
| Provider | Together AI | OpenAI |
| Input / MTok | $0.5 | $0.2 |
| Output / MTok | $1.2 | $1.25 |
| Cache read / MTok | — | $0.02 |
| Context window | 524,288 | — |
| Blended 1M in + 3M out | $4.10 | $3.95 |
| Status | ga | ga |