Model specification · Thinking Machines
Inkling Small
thinkingmachines/inkling-small
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...
SpecificationsReported values
- Context window
- 1.0M
- Maximum output
- 262K
- 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 | free |
|---|---|---|
| Input | $0.450 / M | free / M |
| Output | $1.20 / M | free / M |
Benchmark indexesReported indexes
- Intelligence
- 26.1
- Coding
- 52.9
- Agentic
- 25
- Design Arena Elo
- —
Example workload costsStandard pricing only
| Workload | Input / output | Cache share | Estimated cost |
|---|---|---|---|
| Quick check | 10K / 1K × 1 | 0% | $0.00570 |
| Long analysis | 100K / 4K × 1 | 50% | $0.032 |
| Workday | 20K / 2K × 1,000 | 30% | $9.30 |
More from Thinking MachinesAll Thinking Machines models
| Model | Context | Input / M | Output / M | Intel. |
|---|---|---|---|---|
| Inkling | 1.0M | $1.00 | $4.05 | 25.5 |