8 Models Available

Explore Our Models

From flagship reasoning to full multimodal — pick the right model for every workload.

Flagship

Qwen3-Max

Flagship reasoning model with thinking mode. Best for complex analysis, multi-step reasoning, and advanced coding tasks.

Context
262K
Input
$1.20–$3.00 / 1M (tiered)
Output
$6.00–$15.00 / 1M
ReasoningThinking ModeCodingBatchCache

Qwen3.5-Plus

Balanced multimodal model supporting text, image, and video. Ideal for production workloads.

Context
1M
Input
$0.40 / 1M
Output
$2.40 / 1M
TextImageVideoMultimodal
Popular

Qwen3.5-Flash

Fast and cost-effective with 1M context. Great for high-throughput pipelines.

Context
1M
Input
$0.10 / 1M
Output
$0.40 / 1M
Fast1M ContextCost-Effective

Qwen-Turbo

Ultra-fast and ultra-cheap. Perfect for real-time chat and high-volume inference.

Context
1M
Input
$0.05 / 1M
Output
$0.20 / 1M
Ultra-FastCheapest1M Context

Qwen3-Coder-Plus

Specialized for code generation, debugging, and technical documentation.

Context
Input
See docs
Output
See docs
CodeDebuggingTechnical

Qwen-VL-Max

Advanced vision-language model. Understands images, charts, documents, and screenshots.

Context
131K
Input
$0.80 / 1M
Output
$3.00 / 1M
VisionImage UnderstandingOCR

Qwen-VL-Plus

Lighter vision model for cost-sensitive visual tasks.

Context
Input
$0.21 / 1M
Output
$0.85 / 1M
VisionLightweightCost-Effective

Qwen3-Omni-Flash

Full multimodal: text, image, and audio input. Native speech understanding.

Context
Input
Text $0.43 / Audio $3.00 / 1M
Output
See docs
AudioImageTextSpeech