Using the APIModel Lineup

Model Lineup

MinT lists models by availability status.

Available Models

Model NameTraining TypeArchitectureSizeContext
Qwen/Qwen3-0.6BHybridDenseTiny32k
Qwen/Qwen3-4B-Instruct-2507InstructionDenseCompact32k
Qwen/Qwen3-30B-A3B-Instruct-2507InstructionMoEMedium32k
Qwen/Qwen3-235B-A22B-Instruct-2507InstructionMoELarge32k
moonshotai/Kimi-K2-Instruct*InstructionMoELarge32k
zai-org/GLM-5*ReasoningMoELarge32k

*Contact sales for Kimi-K2 and GLM5 access

Coming Soon

Model NameTraining TypeArchitectureSizeContext
Qwen/Qwen3-30B-A3BHybridMoEMedium32k
Qwen/Qwen3-30B-A3B-BaseBaseMoEMedium32k
Qwen/Qwen3-8BHybridDenseSmall32k
Qwen/Qwen3-8B-BaseBaseDenseSmall32k
deepseek-ai/DeepSeek-V3.1HybridMoELarge32k
deepseek-ai/DeepSeek-V3.1-BaseBaseMoELarge32k
Qwen/Qwen3-VL-30B-A3B-InstructVisionMoEMedium32k
Qwen/Qwen3-VL-235B-A22B-InstructVisionMoELarge32k
π0RoboticsDenseSmall32k

Model Selection Recommendations

  • Low-latency: Qwen3-0.6B or Qwen3-4B-Instruct-2507
  • Balanced quality: Qwen3-30B-A3B-Instruct-2507
  • Frontier scale: Qwen3-235B-A22B-Instruct-2507

Model Categories

By Training Type

  • Hybrid - Mixed general + instruction behavior
  • Instruction - Fine-tuned for instruction following

By Architecture

  • Dense - Traditional transformer architecture
  • MoE (Mixture of Experts) - Sparse activation for efficiency

By Size

  • Tiny: under 1B parameters
  • Compact: 1-4B parameters
  • Medium: ~30B parameters
  • Large: 200B+ parameters

Cost Efficiency

MoE models offer superior cost-efficiency: pricing scales with active parameters, not total model size. For example, a 235B MoE model with 22B active parameters costs the same as a 22B dense model.