Home › Compare › Thinking Machines: Inkling vs Thinking Machines: Inkling Small
Thinking Machines: Inkling vs Thinking Machines: Inkling Small: API Pricing Compared
Comparing Thinking Machines: Inkling and Thinking Machines: Inkling Small: on combined input+output list price, Thinking Machines: Inkling Small is cheaper at $1.65 vs $5.05 per 1M tokens — a difference of $3.4 (67%). Thinking Machines: Inkling costs $1 in / $4.05 out with a 524,288-token context; Thinking Machines: Inkling Small costs $0.45 in / $1.2 out with a 524,288-token context.
| Thinking Machines: Inkling | Thinking Machines: Inkling Small | |
|---|---|---|
| Input /1M | $1 | $0.45 |
| Output /1M | $4.05 | $1.2 |
| Cached input /1M | $0.17 | $0.1 |
| Context window | 524,288 | 524,288 |
| Max output tokens | 471,859 | 262,144 |
| Cost @ 10M in + 2M out / mo | $18.1 | $6.9 |
Estimate your own workload in the cost calculator, or open the full pages for Thinking Machines: Inkling and Thinking Machines: Inkling Small.
Frequently asked questions
Which is cheaper, Thinking Machines: Inkling or Thinking Machines: Inkling Small?
Thinking Machines: Inkling Small is cheaper on combined list price: $1.65 vs $5.05 per 1M tokens (input + output). At 10M input + 2M output tokens per month, Thinking Machines: Inkling costs $18.1 and Thinking Machines: Inkling Small costs $6.9.
Which has the larger context window, Thinking Machines: Inkling or Thinking Machines: Inkling Small?
Thinking Machines: Inkling has a context window of 524,288 tokens; Thinking Machines: Inkling Small has 524,288 tokens. The larger one is Thinking Machines: Inkling.
Price snapshot October 21, 2026, refreshed daily.