T
Inkling (batch)OPEN
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.
Prices update automatically — checked daily against provider list prices.
- $1.76 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 7% of the 189 open-weight models tracked here
- 3 of 3 Thinkingmachines models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Inkling (batch), measured by Artificial Analysis. Higher is better. Measurement mode: xhigh.
For the same budget, Inkling (batch) delivers 3.8 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $1.49 per 1M tokens (median of 19) — this one costs $1.76.
Cheaper and better on this index: Gemini 3.7 Flash · Gemini 3.7 Flash (batch) · DeepSeek V4 Pro 0813 and 15 more
About this model
Inkling (batch) 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 (batch)?
Inkling (batch) 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 42.3 on the Artificial Analysis intelligence index.
Is Inkling (batch) free?
The weights are free and open — you can self-host Inkling (batch) and pay nothing per token. If you prefer a hosted API, list prices are $1 per million input tokens and $4.05 per million output tokens.
What is Inkling (batch) good at?
Independent benchmarks from Artificial Analysis give it GPQA 87.2%, Humanity's Last Exam 31.9%, Long Context Reasoning 73.3%, SciCode 46.1%, τ-Bench Banking 29.1%, Terminal-Bench 55.1%. It is particularly used for code generation.
How fast is Inkling (batch)?
It generates about 69.8 tokens per second, with a median 2.42s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Inkling (batch)?
Yes. Inkling (batch) 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.