Thinking Machines Lab

Inkling

Thinking Machines Lab's flagship open-weight multimodal MoE for reasoning, tool use, and fine-tuning. Available on Tinker (64K and 256K context), Together AI serverless (1M context), and other inference gateways.

ActiveReleased July 15, 2026Available from 3 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: Tinker models & pricing, Inkling model card, Inkling announcement, Inkling on Together AI

Price per 1M tokens
$1.87 in / $4.68 out
Context window262,144
Cache read$0.374 / M
ModalitiesText, Image, Audio → Text
Priced across3 providers

Pricing

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

Billing legStandardLong context
Input$1.87 / M$3.74 / M
Output$4.68 / M$9.36 / M
Cache read$0.374 / M$0.748 / 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
$655
at current list prices
Fresh input$374
Cached input$0.00
Output incl. thinking$281
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
$1.87$4.68$0.374—First-party API
Together AILowest
$1$4.05$0.17—Direct
Together AI
$1$4.05$0.17—via OpenRouter

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $1.87 / $4.68 per 1M since July 17, 2026.

Stop estimating. Track it.

SuperPenguin meters every Inkling 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.