T
Compare
Inkling
Thinking Machines · Multimodal · Released Jul 2026
An open-weight multimodal mixture-of-experts model with 12B active parameters from 276B total parameters and a 524K token context window.
- Strengths
- The mixture-of-experts architecture allows efficient inference by activating only a subset of parameters while maintaining access to the full model capacity for different tasks.
- Best for
- Workloads requiring broad multimodal understanding across text and images where efficient inference and long-context reasoning matter more than maximum performance per token.
- Limitations
- As an open-weight model with 12B active parameters, it trades off raw capability against efficiency compared to larger closed models, and the mixture-of-experts design requires compatible hardware for efficient execution.
Input / 1M
$1.00
Output / 1M
$4.05
Cached input / 1M
$0.17
Context window
524K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in increased 5.3% out decreased 0.0%
- 90d
- in decreased 0.0% out decreased 0.0%
- 1y
- in decreased 0.0% out decreased 0.0%
- Since launch
- in decreased 0.0% out decreased 0.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 30 Aug 2026 | $1.00 | $4.05 | $0.17 | Imported from OpenRouter | openrouter.ai |
| 25 Aug 2026 | $0.95 | $4.05 | $0.16 | Imported from OpenRouter | openrouter.ai |
| 24 Aug 2026 | $1.00 | $4.05 | $0.17 | Imported from OpenRouter | openrouter.ai |
| 23 Aug 2026 | $0.95 | $4.05 | $0.16 | Imported from OpenRouter | openrouter.ai |
| 8 Aug 2026 | $0.95 | $4.05 | $0.16 | Imported from OpenRouter | openrouter.ai |
| 18 Jul 2026 | $1.00 | $4.05 | $0.17 | Imported from OpenRouter | openrouter.ai |