token.app › Compare › Muse Spark 1.2 vs Inkling Small
Muse Spark 1.2 vs Inkling Small
Inkling Small is 3.1× cheaper per token on a blended 3:1 basis. Muse Spark 1.2 accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| Muse Spark 1.2 | Inkling Small | |
|---|---|---|
| Provider | Meta | Thinkingmachines |
| Input $/1M | $1.25 | $0.450 |
| Output $/1M | $4.25 | $1.20 |
| Blended $/1M | $2.00 | $0.637 |
| Context window | 1.0M | 524K |
| Max output | — | 262K |
| Released | Aug 2026 | Jul 2026 |
| Licence | Proprietary | Open weights |
Choose Muse Spark 1.2 if…
- Larger context window (1.0M)
- Newer model (released Aug 2026)
Choose Inkling Small if…
- Costs less per token — $0.637 vs $2.00 blended
- Open weights — self-hostable
FAQ
Which is better, Muse Spark 1.2 or Inkling Small?
We do not hold independently-run benchmark scores covering both Muse Spark 1.2 and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Muse Spark 1.2 cheaper than Inkling Small?
Inkling Small is cheaper: $0.637 versus $2.00 per million tokens blended at 3:1 input:output. Input alone: $1.25 vs $0.450. Output alone: $4.25 vs $1.20.
What context windows do Muse Spark 1.2 and Inkling Small have?
Muse Spark 1.2: 1,048,576 tokens. Inkling Small: 524,288 tokens.
Who makes Muse Spark 1.2 and Inkling Small?
Muse Spark 1.2 is made by Meta. Inkling Small is made by Thinkingmachines.