Qwen: Qwen3 Next 80B A3B Thinking
by QwenQwen: Qwen3 Next 80B A3B Thinking is a large language model from Qwen. It costs $0.150 per million input tokens and $1.20 per million output tokens. Its context window is 262K tokens.
- Input / 1M tokens
- $0.150
- Output / 1M tokens
- $1.20
- Cached input / 1M
- -
- Context window
- 262K
Not supported
tokens
Who serves it cheapest
2 hosts serve Qwen3 Next 80B A3B Thinking. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| GoogleCheapest | $0.150 | $1.20 | 262K | - | 100.0% |
| Alibaba | $0.150 | $1.20 | 131K | - | 100.0% |
The spread between Google and Alibaba is about the same for identical weights. Quantization and context limits differ, so check both columns before switching.
Benchmarks
Independent scores published alongside the catalogue.
- Coding index
- 17.4
About 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...
Specifications
| Model ID | qwen/qwen3-next-80b-a3b-thinking |
|---|---|
| Provider | Qwen |
| Context window | 262K tokens |
| Max output | 236K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | 2025-09-30 |
| Open weights | Yes - Qwen/Qwen3-Next-80B-A3B-Thinking |
| Released | September 11, 2025 |
Cheaper alternatives
Models that cost less than Qwen3 Next 80B A3B Thinking while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Qwen: Qwen3 Next 80B A3B Thinking cost?
$0.150 per million input tokens and $1.20 per million output tokens.
What is the context window of Qwen: Qwen3 Next 80B A3B Thinking?
262K tokens, with up to 236K tokens of output per request.
Which provider serves Qwen: Qwen3 Next 80B A3B Thinking cheapest?
Google at $0.150 per million input tokens - about the same cheaper than Alibaba, the most expensive of the 2 hosts serving it.
Confirm against the source: Qwen official pricing.