Last refreshed 2026-07-15. Next refresh: weekly.
Why use Inkling on Tinker?
Tinker offers Inkling with pay-as-you-go pricing at $1.87/1M input tokens. Tinker is Thinking Machines Lab's managed API platform for fine-tuning and sampling supported foundation models.
Compare Inkling across 2 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: thinkingmachines/Inklingthinkingmachines/InklingRequest example
thinkingmachines/Inkling.Gotchas
- Use provider model ID "thinkingmachines/Inkling", not the LLMReference slug "inkling".
Compare Inkling Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Tinker | $1.87 | $4.68 |
| Baseten API | $1.00 | $4.05 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.87 |
| Output tokens | $4.68 |
Capabilities
About Inkling
Inkling is Thinking Machines Lab's Apache-2.0 open-weight general-purpose multimodal model. It accepts text, image, and audio inputs and generates text with a 1M-token context window. Compare it for Coding, RAG, Agents, Long context, Vision, and JSON / Tool use.
FAQ
What does Inkling cost on Tinker?
On Tinker, Inkling costs $1.87 per 1M input tokens and $4.68 per 1M output tokens.
What is the context window for Inkling on Tinker?
Inkling supports a 64k token context window on Tinker.
How does Tinker compare to other Inkling providers?
Inkling is available from 2 providers. The cheapest input pricing is $1.00/1M tokens from Baseten API.
What API model ID do I use for Inkling on Tinker?
Use the model ID thinkingmachines/Inkling when calling Tinker's API.
Who created Inkling?
Inkling was created by Thinking Machines Lab as part of the Inkling model family.
Is Inkling open source?
Inkling is open source under Apache 2.0 according to the seed data.