Qwen3-235B-A22B-Thinking-2507 is the latest high-reasoning variant of the Qwen3 series, delivering state-of-the-art performance on complex tasks in logic, mathematics, science, coding, and academic benchmarks. It introduces a longer “thinking length,” native 256K context support, and improved instruction-following, tool usage, and alignment with human preferences. Designed for thinking-only mode, it excels at deep reasoning and long-context understanding, making it ideal for applications such as advanced problem-solving, code generation, research, academic work, and agentic tool use.
Immediately run model on pre-configured GPUs and pay-per-token
Learn MoreOn-demand deployments give you dedicated GPUs for Qwen3 235B-A22B Thinking using Fireworks' reliable, high-performance system with no rate limits.
Learn MoreQwen
256k
Available
$0.1