Last refreshed 2026-11-06. Next refresh: weekly.
Why use Inkling 2 Small on Tinker?
Tinker offers Inkling 2 Small with pay-as-you-go pricing at $0.30/1M input tokens. Tinker is Thinking Machines Lab's managed API platform for fine-tuning and sampling supported foundation models.
Input / 1M
$0.30
Output / 1M
$1.00
Cache
read $0.030
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: thinkingmachines/Inkling-2-SmallModel ID
thinkingmachines/Inkling-2-SmallRequest example
Curated snippets for this provider are not sourced yet. Use Tinker documentation with model ID
thinkingmachines/Inkling-2-Small.Gotchas
- Use provider model ID "thinkingmachines/Inkling-2-Small", not the LLMReference slug "inkling-2-small".
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.30 |
| Output tokens | $1.00 |
Capabilities
VisionMultimodalReasoningJSON / Tool useFine-tuning
About Inkling 2 Small
Inkling 2 Small is Thinking Machines Lab's first second-generation Inkling model, released November 5, 2026. It is a 594B-total / 17B-active MoE for text and image inputs with controllable reasoning effort. It is available for inference and fine-tuning on Tinker; downloadable weights are closed at launch.
Get Started
Model Specs
Released2026-11-05
Parameters594B (17B active)
Context256K
ArchitectureMixture of Experts