T
Inkling SmallOPEN
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total.
Prices update automatically — checked daily against provider list prices.
- $0.64 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 31% of the 189 open-weight models tracked here
- 1 of 3 Thinkingmachines models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Inkling Small, measured by Artificial Analysis. Higher is better.
For the same budget, Inkling Small delivers 12 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $1.41 per 1M tokens (median of 20) — this one costs $0.64.
Cheaper and better on this index: Gemini 3.7 Flash (batch) · GPT-5.6 Luna · GPT-5.6 Luna (batch) and 8 more
About this model
Inkling Small is an open-weight AI model by Thinkingmachines. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Inkling Small?
Inkling Small is an AI language model from Thinkingmachines. It is open-weight: you can download it and run it on your own hardware, for free. It scores 41.2 on the Artificial Analysis intelligence index.
Is Inkling Small free?
The weights are free and open — you can self-host Inkling Small and pay nothing per token. If you prefer a hosted API, list prices are $0.45 per million input tokens and $1.2 per million output tokens.
What is Inkling Small good at?
Independent benchmarks from Artificial Analysis give it GPQA 89.5%, Humanity's Last Exam 33.3%, Long Context Reasoning 69.3%, SciCode 48.7%, τ-Bench Banking 18.8%, Terminal-Bench 55.1%. It is particularly used for code generation.
How fast is Inkling Small?
It generates about 61.3 tokens per second, with a median 1.86s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Inkling Small?
Yes. Inkling Small has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.