Model tracker / Thinking Machines Lab
Inkling 2 Small
594B MoE model with 17B active for agentic coding, vision and fine-tuning on Tinker
Inkling 2 Small is a fast model from Thinking Machines Lab, released 5 November 2026. It's in preview. At Thinking Machines Lab it costs $0.30 per million input tokens and $1.00 per million output tokens, with a 262K-token context window.
- Made by
- Thinking Machines Lab
- Released
- 2026-11-05
- Status
- Preview, new
- Tier
- Fast
- Weights
- Closed
- Context window
- 262,144 tokens
- Input
- text, image
Inkling 2 Small price at Thinking Machines Lab
US dollars per million tokens. Blended is 3 input tokens for every output token, one number to compare on.
| Provider | Input | Output | Cached input | Blended | Batch | Checked |
|---|---|---|---|---|---|---|
| Thinking Machines Lab · maker | $0.30 | $1.00 | $0.03 | $0.475 | – | 2026-11-06 |
- Thinking Machines Lab: Tinker serverless inference, in beta; production use is by waitlist. Thinking Machines plans Apache 2.0 weights the week after launch, after external safety testing. Fine-tuning on Tinker is $1.50 per 1M training tokens at 64K context, $3.00 at 256K.
Models like Inkling 2 Small
Other fast models closest in price, at each maker's own price or the cheapest provider.
| Model | Input | Output | Context | Weights |
|---|---|---|---|---|
| Inkling 2 Small | $0.30 | $1.00 | 262K | Closed |
| Step 3.7 Flash StepFun | $0.20 | $1.15 | 256K | Open |
| DeepSeek V4.1 Flash DeepSeek | $0.30 | $1.20 | 1M | Open |
| Muse Glimmer 30B Meta | $0.30 | $1.20 | 131K | Open |
| Gemini 3.1 Flash-Lite Google | $0.25 | $1.50 | 1M | Closed |
| GLM-5.3 FlashX Z.ai | $0.37 | $1.25 | 1M | Open |
Compare them all in the model tracker →
Inkling 2 Small on dbggr
- Claude Code sent users' email addresses to websites; a new check catches only part of it Daily, 2026-11-05
Inkling 2 Small FAQ
How much does Inkling 2 Small cost?
Inkling 2 Small costs $0.30 per million input tokens and $1.00 per million output tokens at Thinking Machines Lab, and $0.03 per million cached input tokens. Prices are list prices in US dollars, last checked 6 November 2026.
What is Inkling 2 Small's context window?
Inkling 2 Small takes up to 262,144 tokens in one request.
Is Inkling 2 Small open weight?
No. Inkling 2 Small is only available through Thinking Machines Lab's API; Thinking Machines Lab doesn't publish the weights.
Where can I use Inkling 2 Small?
Inkling 2 Small is available from Thinking Machines Lab.