Inkling Small

thinkingmachines/inkling-smallEst. 40% off · Standardvs cheapest OpenRouter endpoint for a typical request: ~80k input / 1k output

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...

Standard prices and discounts apply to Standard requests. Requests requiring zero data retention use separate ZDR quotes. Retention depends on the provider serving your request.

Input /M

$0.2678

Estimated price

Output /M

$1.07

Estimated price

Our price (estimated) · in + out$1.34Selected gateway · in + out /M

Context524.3KUpstream catalog

ReleasedJul 302026

Standard price history.

Quotes observed by your selected gateway for this privacy mode.

ROUTE AVAILABLE

Loading route prices…

History begins when this gateway observes an eligible quote. Other routes’ prices are never substituted.

Fee-inclusive route quotes for 1M input + 1M output tokens. Observations are sampled every five minutes and held for up to 24 hours on this gateway instance; restarting it clears history. Gaps mean no observation.

Use this model

Inkling Small thinkingmachines/inkling-small

01
Set up GPU Router
Your coding assistant adds the client and checks model availability.
02
Choose your calls
Switch all matching calls, selected features, or use it for new calls only.
03
Switch and test
Only the calls you choose are migrated. Everything else stays as is.

Paste into your coding assistant. It will ask before switching calls.

What would your workload cost?

Change your token mix to compare the same workload.

Input tokensOutput tokens

Estimated cost · USD$37.2

Direct list$25.2

Cheapest OpenRouter endpoint$37.2

The active OpenRouter endpoint with the lowest input + output cost for this workload.

Our price (estimated)$22.49

Estimated cost of an eligible route on your selected gateway.

Input costOutput cost

Estimated savings with GPU Router$14.71less than the cheapest OpenRouter endpoint

For 80M input + 1M output tokens using our current estimate.

Our price is the cheapest eligible route or live trusted seller offer for this workload, including the routing fee. Final charges depend on the route and actual usage.