Inkling

Thinkingmachines · thinkingmachines/inkling

← Back to leaderboard

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

Inkling ranks #265 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $2.52 blended per million tokens, it is cheaper than 30% of models with published API pricing. Its 524,288-token context window is 2.0× the catalog median (262,144 tokens).

open weightsaudioimagetexttext+image+audio->text

Context

Max context: 524288
Max output: 471859

Pricing

Input / 1M: 1.00
Output / 1M: 4.05
Blend / 1M: 2.52

Quality

Quality index:

Provider

Provider: Thinkingmachines
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $2.52per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$2.52
10,000,000$25.25
100,000,000$252.50

Related models

Same lab, similar price, or similar quality — useful next comparisons.

More from Thinkingmachines

Closest API price