Thinking Machines Lab

Inkling-Small

Thinking Machines Lab's compact open-weight multimodal MoE, with 12B active parameters, controllable reasoning, and up to a 1M-token context window.

ActiveReleased July 30, 2026Available from 4 providers
Tool callingCan invoke external tools and APIs (function calling) mid-response.Structured outputCan return JSON or schema-constrained responses instead of free text.ReasoningUses extended thinking / chain-of-thought for harder multi-step problems.Effort controlLets you dial thinking depth (low / medium / high) to trade cost for quality.Fine-tuningSupports training a custom variant on your own data (vendor fine-tune API or self-hosted open weights).

Source: Inkling-Small model card, Inkling-Small announcement, Inkling-Small model configuration, Thinking Machines structured tool-call renderer, Inkling-Small on Together AI, OpenRouter route limits

Price per 1M tokens
$0.58 in / $1.44 out
Context window1,048,576
Max output262,144
Cache read$0.116 / M
ModalitiesText, Image, Audio → Text
Priced across4 providers

Pricing

Every billing leg from the live catalog, in USD per 1M tokens.

Billing legStandardLong context
Input$0.58 / M$1.16 / M
Output$1.44 / M$2.89 / M
Cache read$0.116 / M$0.232 / M

Long-context rates apply above 65,536 input tokens.

Cost calculator

Billing-grade math over the rate card above, including the thinking tokens most estimates miss.

Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.

Estimated monthly cost
$202
at current list prices
Fresh input$116
Cached input$0.00
Output incl. thinking$86.40
Track this automatically →

Compare providers

The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.

PlatformInput / MOutput / MCache read / MBatchAccess
Thinking Machines
$0.58$1.44$0.116—First-party API
DeepInfraLowest
$0.45$1.2$0.1—via OpenRouter
Together AI
$0.5$1.2$0.1—Direct
Together AI
$0.5$1.2$0.1—via OpenRouter

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $0.58 / $1.44 per 1M since August 10, 2026.

More from Thinking Machines Lab

Other models from the same provider.

Inkling
thinking-machines/inkling
$0.95 / $4.05 in / out per 1M

Stop estimating. Track it.

SuperPenguin meters every Inkling-Small call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.

Get started free

Rates are generated from SuperPenguin's live pricing catalog.