Qwen3 represents the latest generation of large language models in the Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built on extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support. Notable features include the unique ability to seamlessly switch between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within a single model, ensuring optimal performance across diverse scenarios. Qwen3 significantly enhances its reasoning capabilities, outperforming previous models like QwQ (in thinking mode) and Qwen2.5 (in non-thinking mode) on tasks such as mathematics, code generation, and commonsense logical reasoning. It also excels in human preference alignment, particularly in creative writing, role-playing, multi-turn dialogues, and instruction following, offering a more natural, engaging, and immersive conversational experience. Qwen3 showcases expertise in agent capabilities, enabling precise integration with external tools in both modes, achieving leading performance in complex agent-based tasks. With support for over 100 languages and dialects, Qwen3 offers robust multilingual instruction-following and translation capabilities, making it an invaluable tool for a wide range of applications.
Provider
Context Size
Max Output
Cost
Speed
nebius_fast
128K
128K
€NaN/M
155.00 tps
nebius_fdt
128K
128K
€NaN/M
155.00 tps
nebius_slow
128K
128K
€NaN/M
155.00 tps
nebiusf
128K
128K
€NaN/M
155.00 tps
API Usage
Seamlessly integrate our API into your project by following these simple steps: