Back to models
available

Thinking Machines: Inkling

thinkingmachines/inkling

Prices

Input

$1.87 per 1M tokens

low
Input (cached read)

$0.374 per 1M tokens

low
Output

$4.68 per 1M tokens

low

Also available on

The same model, sold by someone else. The price above is the maker's own.

28 sales channels for this model.
ChannelWhatPrice
Microsoft Azure · azure-aiInput$1.10 per 1M tokens
Input (cached read)$0.19 per 1M tokens
Output$4.46 per 1M tokens
DatabricksInput$1.00 per 1M tokens
Input (cache write)$1.00 per 1M tokens
Input (cached read)$0.17 per 1M tokens
Output$4.05 per 1M tokens
Fireworks AI · fireworks-aiInput$1.00 per 1M tokens
Input (cached read, priority)$0.17 per 1M tokens
Input (cached read)$0.17 per 1M tokens
Input (priority)$1.00 per 1M tokens
Output$4.05 per 1M tokens
Output (priority)$4.05 per 1M tokens
OpenRouterInput$1.00 per 1M tokens
Input (cached read)$0.17 per 1M tokens
Output$4.05 per 1M tokens
OpenRouter · thinkingmachinesInput$1.00 per 1M tokens
Input (cached read)$0.17 per 1M tokens
Output$4.05 per 1M tokens
Other · abacusInput$3.74 per 1M tokens
Input (cached read)$0.748 per 1M tokens
Output$9.36 per 1M tokens
Other · aimlapiInput$1.06 per 1M tokens
Input (cached read)$0.1799 per 1M tokens
Output$4.28 per 1M tokens
Other · basetenInput$1.00 per 1M tokens
Input (cached read)$0.17 per 1M tokens
Output$4.05 per 1M tokens
Other · commandcodeInput$1.00 per 1M tokens
Input (cached read)$0.17 per 1M tokens
Output$4.05 per 1M tokens
Other · deepinfraInput$0.95 per 1M tokens
Input (cached read)$0.16 per 1M tokens
Output$4.05 per 1M tokens
Other · edenaiInput (cached read) (host: deepinfra)$0.16 per 1M tokens
Input (cached read) (host: together-ai)$0.17 per 1M tokens
Input (host: deepinfra)$0.95 per 1M tokens
Input (host: together-ai)$1.00 per 1M tokens
Output (host: deepinfra)$4.05 per 1M tokens
Output (host: together-ai)$4.05 per 1M tokens
Other · huggingfaceInput$1.00 per 1M tokens
Output$4.05 per 1M tokens
Other · hyperInput$1.09 per 1M tokens
Input (cached read)$0.1851 per 1M tokens
Output$4.41 per 1M tokens
Other · impossiblInput$1.87 per 1M tokens
Input (cached read)$0.374 per 1M tokens
Output$4.68 per 1M tokens
Other · kiloInput$1.00 per 1M tokens
Input (cached read)$0.17 per 1M tokens
Output$4.05 per 1M tokens
Other · llmgatewayInput$0.95 per 1M tokens
Input (cached read)$0.16 per 1M tokens
Output$4.05 per 1M tokens
Other · llmgateway-providersInput (cached read) (host: deepinfra)$0.16 per 1M tokens
Input (cached read) (host: together-ai)$0.17 per 1M tokens
Input (host: deepinfra)$0.95 per 1M tokens
Input (host: together-ai)$1.00 per 1M tokens
Output (host: deepinfra)$4.05 per 1M tokens
Output (host: together-ai)$4.05 per 1M tokens
Other · llmtrInput$1.87 per 1M tokens
Input (cached read)$0.374 per 1M tokens
Output$4.68 per 1M tokens
Other · merge-gatewayInput$1.00 per 1M tokens
Input (cached read)$0.17 per 1M tokens
Output$4.05 per 1M tokens
Other · nano-gptInput$1.00 per 1M tokens
Input (cached read)$0.17 per 1M tokens
Output$4.05 per 1M tokens
Other · neonInput$1.00 per 1M tokens
Input (cached read)$0.17 per 1M tokens
Output$4.05 per 1M tokens
Other · nvidiaInput$0.00 per 1M tokens
Output$0.00 per 1M tokens
Other · openrouterInput$1.00 per 1M tokens
Input (cached read)$0.17 per 1M tokens
Output$4.05 per 1M tokens
Other · requestyInput$1.87 per 1M tokens
Input (cached read)$0.374 per 1M tokens
Output$4.68 per 1M tokens
Other · together-aiInput$1.00 per 1M tokens
Input (cached read)$0.17 per 1M tokens
Output$4.05 per 1M tokens
Other · togetheraiInput$1.00 per 1M tokens
Input (cached read)$0.17 per 1M tokens
Output$4.05 per 1M tokens
Other · veniceInput$0.5625 per 1M tokens
Input (cached read)$0.125 per 1M tokens
Output$1.50 per 1M tokens
Other · vercelInput$1.00 per 1M tokens
Input (cached read)$0.17 per 1M tokens
Output$4.05 per 1M tokens

Specifications

Provider
thinkingmachines
Context window
524,288
Max output tokens
32,768
Open weights
yes
Released
07/15/2026
Retires
no date announced
First seen by this tracker

Price history

No price of this model has changed since we started tracking it.

Input
1.87 per 1M tokens, unchanged since 09/14/2026
Output
4.68 per 1M tokens, unchanged since 09/14/2026
Input (cached read)
0.374 per 1M tokens, unchanged since 09/14/2026

Last updated 11/16/2026, 01:12