Mind LabLanguage modelWeights available
Macaron-V1.1
21out of 100first value
usage data only, range 8 to 35
Summary
Macaron-V1.1 is Mind Lab's open-weights text model built on GLM-5.3. Four LoRA specialists cover chat, agent tasks, coding, and Generative UI. Mind Lab released it on September 22, 2026.
Mint Recursive and Alibaba Cloud Model Studio provide API access. Alibaba also lists the ID mindlab/macaron-v1.1-coding-venti. The documentation does not confirm a separate checkpoint for it.
On this page
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
The 100 most popular models of this category, 0 to 100, higher is more popular
20 of 101 models
As of November 2026 · Source: gradually.ai popularity index
Over time
First value from November 16, 2026. The timeline appears from the second week.
What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.
Similar models
More models of the same kind as Macaron-V1.1, chosen by model line, developer, size, price and release date.
- Macaron-V1-TallMind Lab · same developer
- Macaron-V1-VentiMind Lab · same developer
- Macaron-V1-Coding-VentiMind Lab · same developer
- DeepSeek-V4.1-FlashDeepSeek · released around the same time
- GLM-5.3Z.ai · released around the same time
- GLM-5.3-FlashZ.ai · released around the same time
- Kimi K3Moonshot AI · released around the same time
- MiMo V2.6 FlashXiaomi · released around the same time
All specifications
Architecture
- Architecture
- GLM-5.3 base with four LoRA specialists for chat, agent tasks, coding, and Generative UI.
- Source: Architecture
Input and output
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
- Weights license
- MIT license according to the model card. Any applicable base-model and dependency requirements must also be observed.
- Source: Weights license
- Shutdown
- None announced
- no source
API
- API capabilities
- Alibaba Cloud Model Studio supports function calling, structured outputs, prefix completion, and context caching. Web search and batch inference are unsupported there.
- Source: API capabilities
Further details
- Additional API model ID
- Mint Recursive also lists macaron-v1.1-coding-venti. The sources do not describe a separate V1.1 checkpoint for this API ID.
- Source: Additional API model ID
- Alibaba coding API model ID
- Alibaba lists text and image input for mindlab/macaron-v1.1-coding-venti. The API ID alone does not establish a separate V1.1 checkpoint.
- Source: Alibaba coding API model ID
- Published model scale
- Mind Lab gives 752B as the release scale: a 744B GLM-5.3 base plus four LoRA specialists labeled 2B each. The sources present this as an architecture or release scale, not as a simple, unambiguous total for the checkpoint.
- Source: Published model scale
- Singapore API context and output limits
- 1,048,576-token context and input limit, 131,072-token output limit, including thinking mode.
- Source: Singapore API context and output limits
- Regional API availability
- Alibaba Cloud Model Studio lists the API IDs in Singapore under its international deployment scope from November 16, 2026.
- Source: Regional API availability
Prices
- Singapore API pricing
- International deployment scope, original rates excluding limited-time promotions: $1.19 input and $3.74 output per 1 million tokens. Implicit cache hits, explicit cache creation with a 5-minute TTL, and explicit cache hits each cost $0.22 per 1 million tokens.Source
Frequently asked questions about Macaron-V1.1
How large is the context window of Macaron-V1.1?
1.05 M tokens. That is how much text Macaron-V1.1 reads at once, about 1,570 A4 pages.
Page count as a rule of thumb from Artificial Analysis
Can I run Macaron-V1.1 locally?
Yes, the weights are open.
Stated by Mind Lab
- Open weights
- yes
- License
- MIT license according to the model card. Any applicable base-model and dependency requirements must also be observed.
- Parameters
- n/a
- active per token
- n/a