Inkling vs Inkling Small
Inkling (Thinking Machines) and Inkling Small (Thinking Machines) are listed at different prices. Inkling Small costs less: $0.45 per 1M input tokens and $1.20 per 1M output tokens, against $1.00 and $4.05 for Inkling. Both hold 524,288 tokens of context. Inkling can write up to 471,859 tokens in one response, against 262,144 for Inkling Small. Both accept text, images and audio and produce text.
Thinking Machines: Inkling and Thinking Machines: Inkling Small both accept text, images, and audio, produce text, and support tools and reasoning. They share a 524,288-token context window; Inkling allows up to 471,859 output tokens, while Inkling Small allows up to 262,144.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Inkling | Inkling Small |
|---|---|---|
| Maker | Thinking Machines | Thinking Machines |
| Added to catalog | 17 Jul 2026 | 30 Jul 2026 |
| Input, per 1M tokens | $1.00 | $0.45 |
| Output, per 1M tokens | $4.05 | $1.20 |
| Cached input read, per 1M | $0.17 | $0.10 |
| Context windowTokens | 524,288 | 524,288 |
| Max outputTokens | 471,859 | 262,144 |
| Accepts | audio, image, text | audio, image, text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | No | No |
| Reasoning effort control | Yes | Yes |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | Inkling | Inkling Small |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0017 | $0.0006 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.028 | $0.012 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.038 | $0.016 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.156 | $0.069 |
Which to choose
Choose Inkling if
- You need longer answers in one response: 471,859 tokens against 262,144
Choose Inkling Small if
- Input tokens cost less: $0.45 against $1.00 per 1M
- Output tokens cost less: $1.20 against $4.05 per 1M
- Cached input costs less: $0.10 against $0.17 per 1M
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.