All models
Thinkingmachines
Inkling Small fastruns locally
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...
Input / 1M
$0.45
USD per million tokens
Output / 1M
$1.20
USD per million tokens
Est. cost / token
$0.000000638
$0.64 per 1M, 3:1 mix
Context window
524K
max output 262K
Major features
VisionOpen weightsCachingReasoningTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision3
- long context4
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 122 GB |
| Q3_K_M | fair | 142 GB |
| Q4_K_Mrecommended | good | 176 GB |
| Q5_K_M | very good | 204 GB |
| Q6_K | excellent | 234 GB |
| Q8_0 | near-lossless | 302 GB |
| F16 | lossless | 564 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.45 | $1.20 | $0.10 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.45
- Output
- $1.20
- Cached input
- $0.10
- Blended (3:1)
- $0.64
Details
- Company
- Thinkingmachines
- Version
- —
- Family
- Inkling
- Released
- 2026-07-30
- Parameters
- 266B
- Max output
- 262K
- Open weights
- Yes
- Inputs
- audio, image, text
- Last synced
- 32 min ago