Head to head
Inkling Small vs Gemini 3.1 Flash-Lite
On a blended workload of one million input tokens and three million output tokens, Inkling Small is 1.2× cheaper than Gemini 3.1 Flash-Lite.
| Inkling Small | Gemini 3.1 Flash-Lite | |
|---|---|---|
| Provider | Together AI | |
| Input / MTok | $0.5 | $0.25 |
| Output / MTok | $1.2 | $1.5 |
| Cache read / MTok | — | $0.025 |
| Context window | 524,288 | — |
| Blended 1M in + 3M out | $4.10 | $4.75 |
| Status | ga | ga |