Qwen: Qwen3 Next 80B A3B Thinking
qwen/qwen3-next-80b-a3b-thinking
ReasoningToolsJSON
Intelligence
—
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.150
86th cheapest
Context
262K
33K max out
How it compares
Cheaper than74%
of all ranked models
Overview
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...
Providers & pricing (3)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| $0.150 | $1.20 | 262K | — | |
| Nebiusfp8 | $0.150 | $1.20 | 128K | — |
| Alibabafp8 | $0.150 | $1.20 | 131K | — |
Specifications
Context window262K
Max output33K
Knowledge cutoffSep 2025
Input modalitiestext
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsQwen/Qwen3-Next-80B-A3B-Thinking ↗
Qwen3 Next 80B A3B Thinking FAQ
How much does Qwen3 Next 80B A3B Thinking cost?
Qwen3 Next 80B A3B Thinking costs $0.150 per million input tokens and $1.20 per million output tokens via OpenRouter, making it 86th cheapest of 332 paid models.
What is Qwen3 Next 80B A3B Thinking's context window?
Qwen3 Next 80B A3B Thinking supports a 262K-token context window and can output up to 33K tokens. It accepts text input.
More from qwen
All Qwen3 Next 80B A3B Thinking alternatives →Compare head-to-head
Qwen: Qwen3 Next 80B A3B Thinking vs Qwen: Qwen3.7 FlashQwen: Qwen3 Next 80B A3B Thinking vs Qwen: Qwen3.7 PlusQwen: Qwen3 Next 80B A3B Thinking vs Qwen: Qwen3.7 MaxQwen: Qwen3 Next 80B A3B Thinking vs Qwen: Qwen3.5 Plus 2026-04-20Qwen: Qwen3 Next 80B A3B Thinking vs Qwen: Qwen3.6 FlashQwen: Qwen3 Next 80B A3B Thinking vs Qwen: Qwen3.6 35B A3B