Model specification · Thinking Machines
Inkling
thinkingmachines/inkling
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...
SpecificationsReported values
- Context window
- 1.0M
- Maximum output
- —
- Architecture
- text+image+audio->text
- Tokenizer
- Other
- Knowledge cutoff
- —
- Moderated
- No
- Input modalities
- text image audio
- Output modalities
- text
Full pricingUSD where reported
| Price | Standard |
|---|---|
| Input | $1.00 / M |
| Output | $4.05 / M |
Benchmark indexesReported indexes
- Intelligence
- 40.7
- Coding
- 52.1
- Agentic
- 32.3
- Design Arena Elo
- 1243
Example workload costsStandard pricing only
| Workload | Input / output | Cache share | Estimated cost |
|---|---|---|---|
| Quick check | 10K / 1K × 1 | 0% | $0.014 |
| Long analysis | 100K / 4K × 1 | 50% | $0.075 |
| Workday | 20K / 2K × 1,000 | 30% | $23.12 |
More from Thinking MachinesAll Thinking Machines models
| Model | Context | Input / M | Output / M | Intel. |
|---|---|---|---|---|
| Inkling Small | 524K | $0.500 | $1.20 | 40.2 |