Compare provider pricing

Compare provider pricing per 1 million tokens: input on the horizontal axis and output on the vertical axis. Dashed lines show official pricing. A point down and to the left is cheaper on both.

Base pricing

6
Newest pricing check Nov 18, 2026.

Published pricing

Tinker Serverless inference · Beta
  • Serverless inference Beta, 256K context. Production access uses a waitlist. Training is separate: USD 1.50/MTok at 64K or USD 3.00/MTok at 256K. Weights are closed at launch; Apache 2.0 release is planned after safety testing.
Tinker Serverless inference · Beta
ComponentOfficial priceBilling unit
InputUSD 0.3per million tokens
OutputUSD 1per million tokens
Cache readUSD 0.03per million tokens

Provider pricing

1

Inkling 2 Small · Specifications

Specifications
Availability / pricingInkling 2 Small
Reported product launch2026-11-05 · Official launch · Thinking Machines Lab
Total parameters (billions)594
Active parameters (billions)17
Predecessor / base modelInkling Small
API model IDthinkingmachines/Inkling-2-Small:peft:262144:sampling-nvfp4
Input modalitiestext / image
Output modalitiestext
reasoning_effort takes effectYes
Official source · checked2026-11-13
[2][3][4]

Questions about Inkling 2 Small pricing

Sources & notes

  1. [1]
  2. [2]
  3. [3]
  4. [4]