Qwen3 Max
Overview
Overview
Qwen3 Max is the flagship model in the Qwen3 series, designed for maximum performance across all tasks. It excels in reasoning, mathematics, coding, and complex problem-solving while maintaining strong multilingual capabilities. Optimized for production use cases requiring the highest quality outputs.
Qwen3 Max was released on December 15, 2025. API access is available through Novita.
Performance
Timeline
ReleasedUnknown
Knowledge CutoffUnknown
Specifications
Parameters
1000.0B
License
Proprietary
Training Data
Unknown
Benchmarks
Benchmarks
Qwen3 Max Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Mon Feb 23 2026Notice missing or incorrect data?Start an Issue discussion→
Pricing
Pricing
Pricing, performance, and capabilities for Qwen3 Max across different providers:
| Provider | Input ($/M) | Output ($/M) | Max Input | Max Output | Latency (s) | Throughput | Quantization | Input | Output |
|---|---|---|---|---|---|---|---|---|---|
 Novita | $0.50 | $5.00 | 256.0K | 131.1K | — | — | — | Text Image Audio Video | Text Image Audio Video |
API Access
API Access Coming Soon
API access for Qwen3 Max will be available soon through our gateway.
Recent Posts
Recent Reviews
Blog Posts
FAQ
Common questions about Qwen3 Max
Qwen3 Max was released on December 15, 2025 by Qwen.
Qwen3 Max was created by Qwen.
Qwen3 Max has 1000.0 billion parameters.
Qwen3 Max is released under the Proprietary license.