M
MINDLAB / mindlab/macaron-v1.1-venti-pro

Macaron V1.1 Venti Pro

A MindLab model available through Model Studio in Singapore from November 20. It combines text and image for conversation, coding and agents, with a 1,048,576-token context and up to 131,072 output tokens. This date refers to availability on this service.

01 / SUMMARY

The essential

ORIENTATIONReasoning and agents with vision

Primary use stated or inferred cautiously from official documentation.

CONTEXT1.048.576 tokens

Maximum input capacity when published by the source.

EXIT131,072 tokens

Documented maximum generation limit.

ACCESSAlibaba Cloud Model Studio

Verified availability channels.

MODEL TYPEMultimodal · Text and reasoning · Code

Primary functional family and verified specialties.

LICENSEProprietary

Declared terms for API access, model weights, or self-hosting.

02 / TECHNICAL SHEET

Limits and integration

API IDmindlab/macaron-v1.1-venti-pro
Model typeMultimodal · Text and reasoning · Code
Access modelPaid proprietary
LicenseProprietary
DeploymentHosted API
Release20 NOV 2026
Knowledge cutoffNot published
EntranceText · Image
ExitText
Context window1.048.576 tokens
maximum output131,072 tokens
Reasoninglow, medium, high, xhigh, max
Published toolsFeatures
Structured OutingsStructured Outings
Batch processingUnavailable
Prompt cacheAvailable
Fine-tuningUnavailable
Verified platformsAlibaba Cloud Model Studio
BEST SUITED FOR

Chat, coding and functions through OpenAI- and Anthropic-compatible APIs.

WORTH MONITORING

Requires activation and authorization in Singapore. The specification lists 600 RPM and 5 million TPM; actual quotas depend on the account. No native web search, Batch or fine-tuning. Input and output limits cannot be added to enlarge the context window.

03 / CAPABILITIES

What it can do

01

Orientation

Chat, coding and functions through OpenAI- and Anthropic-compatible APIs.

02

Context

1.048.576 tokens · 131,072 tokens

03

Tools and integration

Features

04

Access

Alibaba Cloud Model Studio

Input modalities
TextImage
04 / PRICES

Documented cost

ConceptWorthUnit/condition
Standard inputUSD 2 / 1M tokensStandard API rate
Cached inputUSD 0.10 / 1M tokensReading reused prefixes
Cache write or storageNot publishedThe condition varies by provider
Standard outputUSD 10 / 1M tokensMay include reasoning tokens
Batch inputNot publishedAsynchronous processing
Batch outputNot publishedAsynchronous processing

Original Singapore tariff: USD 2 input and USD 10 output per million tokens. Cache reads and explicit creation with a five-minute TTL cost USD 0.10 per million. Reasoning is billed as output; promotions are not assumed.

i Prices change and may depend on level, region or context length. Check the source before making a decision.

05 / EVALUATIONS

How to read the results

“

No verified quantitative score for this version.

i No verified quantitative score for this version.

Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.

06 / VERSIONS

Chronology

mindlab/macaron-v1.1-venti-pro

Available on Model Studio in the Singapore region.

07 / SOURCES

Traceability