Skip to main content
Text generation

mindlab/macaron-v1-tall

mindlab/macaron-v1-tall is built on MindLab's MoL architecture. It is a faster, lighter, and more cost-effective small model, fully optimized for Chat, Agent, Coding, and UI4A experiences.

Inference Service Provider

The inference service provider for mindlab/macaron-v1-tall is MindLab.

Model Capabilities

CapabilitySupportCapabilitySupport
Input ModalityTextOutput ModalityText
Model ExperienceUnsupportedFunction CallingSupported
Structured OutputsSupportedWeb SearchUnsupported
Prefix CompletionSupportedContext CachingSupported
Batch InferenceUnsupportedFine-tuningUnsupported

Context Limits

ParameterValueParameterValue
Max Input Length262144Max Output Length65536
Context Window262144Max Input Length (Thinking Mode)262144
Max Output Length (Thinking Mode)65536Max Chain-of-Thought Length65536

Pricing

This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit QwenCloud console for promotional offers.
  • Singapore
Scope: International
Billing ItemPrice (USD)Unit
Input0.45Per 1M tokens
Output2.6Per 1M tokens
Input (Implicit Cache Hit)0.08Per 1M tokens
Explicit Cache Creation (5-minute TTL)0.08Per 1M tokens
Explicit Cache Hit0.08Per 1M tokens

Rate Limits

  • Singapore
Scope: International
ParameterValue
RPM (Requests Per Minute)300
TPM (Tokens Per Minute)3,000,000