Qwen3 235B A22B
Overview
Qwen3 235B A22B is a large language model developed by Alibaba, featuring a Mixture-of-Experts (MoE) architecture with 235 billion total parameters and 22 billion activated parameters. It achieves competitive results in benchmark evaluations of coding, math, general capabilities, and more, compared to other top-tier models.
Qwen3 235B A22B was released on April 29, 2025. API access is available through 4 providers, including Fireworks, DeepInfra and others.
Performance
Timeline
Specifications
Benchmarks
Qwen3 235B A22B Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Wed Dec 24 2025Pricing
Pricing, performance, and capabilities for Qwen3 235B A22B across different providers:
| Provider | Input ($/M) | Output ($/M) | Max Input | Max Output | Latency (s) | Throughput | Quantization | Input | Output |
|---|---|---|---|---|---|---|---|---|---|
 Fireworks | $0.10 | $0.10 | 128.0K | 128.0K | 0.78 | 68.17 tok/s | — | Text Image Audio Video | Text Image Audio Video |
 DeepInfra | $0.20 | $0.60 | 128.0K | 128.0K | 1.23 | 21.74 tok/s | — | Text Image Audio Video | Text Image Audio Video |
 Novita | $0.20 | $0.80 | 128.0K | 128.0K | 1.02 | 38.51 tok/s | — | Text Image Audio Video | Text Image Audio Video |
 Together | $0.20 | $0.60 | 128.0K | 128.0K | 0.79 | 23.74 tok/s | — | Text Image Audio Video | Text Image Audio Video |
Price Comparison for Qwen3 235B A22B
Price per 1M input tokens (USD), lower is better
llm-stats.com - Wed Dec 24 2025Throughput Comparison for Qwen3 235B A22B
Tokens per second, higher is better
llm-stats.com - Wed Dec 24 2025Latency Comparison for Qwen3 235B A22B
Time to first token (s), lower is better
llm-stats.com - Wed Dec 24 2025Qwen3 235B A22B API Providers: Price vs Throughput
API Access
API Access Coming Soon
API access for Qwen3 235B A22B will be available soon through our gateway.
Recent Posts
Recent Reviews
FAQ
Common questions about Qwen3 235B A22B