Inkling

Thinking Machines released 2026-07-17

$1.73 per million tokens, balanced

Gemini 3.7 Flash scores higher and costs less — but you would give something up.

+13.7 on the capability index and 57% cheaper ($0.750/M against $1.73/M). What you lose:

  • 262K → 66K max output

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$0.950/M
Output$4.05/M
Cached input$0.160/M

Independent scores

Intelligence42.3
Coding52.1
Agentic34.1
LMArena Elo1439.2default

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 window1.0M
Max output262K
Input modestext, image, audio
Tool useyes
Reasoningoptional

Provenance

Price sourceopenrouter.ai
Fetched2026-08-24
Quality dataverified

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,...

Markdown for LLMs