← Compare models
Open all in the calculator — adjust volume and token counts →
GPT-5.4 Nano vs Inkling Small
List-price comparison ·GPT-5.4 Nano details ·Inkling Small details
For a typical workload (100,000 requests / mo), GPT-5.4 Nano is the cheapest — 42% less than the priciest here ($74.00/mo vs $127.20/mo).
| GPT-5.4 Nano | Inkling Small | |
|---|---|---|
| Input / 1M tokens | $0.200 | $0.580 |
| Output / 1M tokens | $1.25 | $1.44 |
| Typical request (1,200 in + 400 out) | $0.0007 | $0.0013 |
| Context window | 400k tokens | 524,288 tokens |
| Max output | 128k tokens | 262,144 tokens |
| Quality score | 62/100 | 58/100 |
| Tier | Flash | Flash |
| Provider | OpenAI | Thinking Machines |
Projected monthly cost
| Requests / mo | GPT-5.4 Nano | Inkling Small |
|---|---|---|
| 1,000 | $0.74 | $1.27 |
| 10,000 | $7.40 | $12.72 |
| 100,000 | $74.00 | $127.20 |
GPT-5.4 Nano
Cheapest OpenAI option for high-throughput classification, tagging, and routing — ideal as a first-pass filter before a stronger model.
Limited reasoning depth means it should be treated as a triage layer, not a final answer source, for anything business-critical.
Inkling Small
Auto-synced from OpenRouter — no editorial write-up yet.
More comparisons
Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.