Inkling Small
Thinking Machines released 2026-07-30
DeepSeek V4 Flash 0731 scores higher and costs less — but you would give something up.
+10.6 on the capability index and 84% cheaper ($0.105/M against $0.637/M). What you lose:
- no image, audio input
Capability scores do not measure context length, output ceiling or which inputs a model accepts, so a higher score does not mean a drop-in replacement.
The same model via free is 100% cheaper (free/M) — same weights, different latency.
Every price dimension
| Input | $0.450/M |
|---|---|
| Output | $1.20/M |
| Cached input | $0.100/M |
Independent scores
| Intelligence | 41.2 |
|---|---|
| Coding | 52.9 |
| Agentic | 31.9 |
| LMArena Elo | 1411.7default |
Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.
Capability
| Context window | 1.0M |
|---|---|
| Max output | 262K |
| Input modes | text, image, audio |
| Tool use | yes |
| Reasoning | optional |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
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...