Inkling
language modelThinkingmachines
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,... License: apache-2.0.
Key facts
| Made by | Thinkingmachines |
|---|---|
| Type | language model |
| Released | July 14, 2026 |
| License | apache-2.0 |
| Reads at once | 524,288 tokens |
| Price (API, per million tokens) | $1 in · $4.05 out |
| Input → output | text, image, audio → text |
| Downloads (recent) | 1.7M |
| Likes on Hugging Face | 1.8K |
Questions about Inkling
Who makes Inkling?
Inkling is made by Thinkingmachines.
When was Inkling released?
We first saw Inkling listed on July 14, 2026.
How much does Inkling cost?
Through OpenRouter it costs $1 per million input tokens and $4.05 per million output tokens. Prices change, so check the provider before you build on it.
How much text can Inkling read at once?
Up to 524,288 tokens, roughly 393.2K words.
More from Thinkingmachines
Inkling SmallThinkingmachines · language model
Jul 27, 2026released
Other language models
gpt2Openai Community · language model
Mar 2, 2022released
Qwen3.8Alibaba (Qwen) · language model
Aug 5, 2026released
Qwen3 VLAlibaba (Qwen) · language model
Sep 23, 2025released
Qwen2.5 VLAlibaba (Qwen) · language model
Jan 26, 2025released
optMeta · language model
May 11, 2022released
Qwen3.6Alibaba (Qwen) · language model
Apr 15, 2026released
Ollamaollama · language model
Jun 26, 2023released
pythiaEleutherAI · language model
Feb 8, 2023released
Modelcast collects this page automatically from public sources (OpenRouter, Hugging Face). Facts are copied from those sources, not written by the maker. Not affiliated with Thinkingmachines.