Qwen3 Next 80B A3B Thinking
Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic planning, and reports strong results across knowledge, reasoning, coding, alignment, and multilingual evaluations. Compared with prior Qwen3 variants, it emphasizes stability under long chains of thought and efficient scaling during inference, and it is tuned to follow complex instructions while reducing repetitive or off-task behavior. The model is suitable for agent frameworks and tool use (function calling), retrieval-heavy workflows, and standardized benchmarking where step-by-step solutions are required. It supports long, detailed completions and leverages throughput-oriented techniques (e.g., multi-token prediction) for faster generation. Note that it operates in thinking-only mode.
qwen/qwen3-next-80b-a3b-thinking
- Context
- 262k tokens
- Completion cap
- 32,768
- Tools
- Yes
- JSON
- Yes
- Released
- 2025-09-11
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen3-next-80b-a3b-thinking",
"messages": [{"role": "user", "content": "Hola"}]
}'Get an API keyFrequently asked questions
- What is Qwen3 Next 80B A3B Thinking?
- Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic planning, and reports strong results across knowledge, reasoning, coding, alignment, and multilingual evaluations. Compared with prior Qwen3 variants, it emphasizes stability under long chains of thought and efficient scaling during inference, and it is tuned to follow complex instructions while reducing repetitive or off-task behavior. The model is suitable for agent frameworks and tool use (function calling), retrieval-heavy workflows, and standardized benchmarking where step-by-step solutions are required. It supports long, detailed completions and leverages throughput-oriented techniques (e.g., multi-token prediction) for faster generation. Note that it operates in thinking-only mode. Qwen3 Next 80B A3B Thinking runs on the Geek Hub API (OpenAI-compatible). Model id: qwen/qwen3-next-80b-a3b-thinking.
- Is Qwen3 Next 80B A3B Thinking free?
- No. Input is $0.1635 per 1M tokens and output is $1.3081 per 1M tokens on Geek Hub (markup included).
- What is the context length of Qwen3 Next 80B A3B Thinking?
- Qwen3 Next 80B A3B Thinking has a 262k tokens context window. It supports up to 32,768 completion tokens.
- Does Qwen3 Next 80B A3B Thinking support tool calling and structured outputs?
- Qwen3 Next 80B A3B Thinking accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
- When was Qwen3 Next 80B A3B Thinking released?
- Qwen3 Next 80B A3B Thinking was released on 2025-09-11.
More models from Qwen
Qwen Plus 0728Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.
Qwen Plus 0728 (thinking)Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.
Qwen-PlusQwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.
Qwen2.5 72B InstructQwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabi
Qwen2.5 7B InstructQwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabil
Qwen2.5 Coder 32B InstructQwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Sig