ThinkingmachinesVision

Inkling Small pricing

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... Live index: 4 priced offers. Best input $0.450 per million tokens from DeepInfra. Best output $1.20 per million tokens from Baseten.

524K context·4 providers·verified Sep 25, 2026
Best input$0.450per 1M tokens · DeepInfra
Best output$1.20per 1M tokens · Baseten

Pricing across providers

Every row is a seller of Inkling Small with token pricing we track. The cheapest input in this snapshot is from DeepInfra. The bar chart shows the same input and output dollars per million for a quick scan.

B
Baseten
Input / 1M
$0.500
Output / 1M
$1.20
Cached in: $0.100
D
DeepInfra
Input / 1M
$0.450
Output / 1M
$1.20
Cached in: $0.100
O
Openrouter
Input / 1M
$0.450
Output / 1M
$1.20
Cached in: $0.100
TA
Together AI
Input / 1M
$0.500
Output / 1M
$1.20
Cached in: $0.100

Input vs output · per provider

Cost calculator

Pick any of the providers above and type how many tokens you expect per day, week, or year. We turn that into rough dollar totals for Inkling Small.

Provider

In: $0.500/M·Out: $1.20/M·Cache: $0.100/M

0.050000¢ / req

0.060000¢ / req

Daily
$11
Monthly
$330
Annual
$4.0K

Model specifications

Quick spec sheet for Inkling Small before you dive back into pricing. Reported under Thinkingmachines.

Context window
524,288 tokens
Max output
262,144 tokens
Vision (images)
Yes
Tool / function calling
No
Streaming
Yes
Released
Jul 2026
Primary provider
Thinkingmachines
Model family
N/A

Compare Inkling Small

Open a pair page to see Inkling Small next to another model with a shared provider matrix. 6 shortcuts below.

Locked

Compare with

Pick a model on both sides.

Popular Inkling Small comparisons

Frequently asked questions

Quick frequently asked items for Inkling Small pricing and limits. The short model note from our index: 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...

Yes. Inkling Small is available on Baseten, DeepInfra, Openrouter, Together AI.

Related models

Models close to Inkling Small by family, provider, and context window — each with live pricing in our catalog.