Qwen3 Coder
Chat Completions API
qwen3-coder
Chat Completions API
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. Optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. Features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts), and supports variable pricing based on context length.
Оплата по факту использования этой модели. Подробнее здесь.
Входные токены (1 млн)
$0.264
Выходные токены (1 млн)
$1.056
Возможности
Входные модальности
Текст
Выходные модальности
Текст
Параметры
Параметры, доступные в API-запросах
Frequency PenaltyLogit BiasLogprobsMax Completion TokensPresence PenaltyResponse FormatStopTemperatureTop PToolsTool ChoiceReasoning Effort