Qwen3 Next 80B A3B Thinking
Qwen3 Next 80B A3B Thinking is Alibaba's language model with a 262K context window and up to 66K output tokens, available from 10 providers, starting at $0.098 / 1M input and $0.780 / 1M output. A thinking-mode variant of the Qwen3 Next MoE model with 80B total and 3B activated parameters, featuring hybrid attention for extended chain-of-thought reasoning.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
 OpenRouter | $0.098 | $0.780 | — | — |
 DeepInfra | $0.140 | $1.40 | — | — |
Alibaba Qwen | $0.150 | $1.20 | $0.075 | $0.600 |
 Google Gemini | $0.150 | $1.20 | — | — |
 Google Vertex AI | $0.150 | $1.20 | — | — |
 Hugging Face | $0.150 | $1.50 | — | — |
 Novita | $0.150 | $1.50 | — | — |
 Together AI | $0.150 | $1.50 | — | — |
 Vercel AI Gateway | $0.150 | $1.20 | — | — |
 Fireworks AI | $0.900 | $0.900 | — | — |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Qwen3 Coder Next | 262K | $0.110 | $0.800 | Available | |
| Qwen3 Next 80B A3B Thinking | 262K | $0.098 | $0.780 | Current | |
| Qwen3 Next 80B A3B Instruct | 262K | $0.090 | $0.900 | Available |