- Input price
- $0.09 / 1M tokens
- Output price
- $1.10 / 1M tokens
- Context window
- 262K tokens
- Longest reply
- 16K tokens
About this model
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
Description from the model’s public catalogue listing.
Capabilities
- Reads
- Text
- Writes
- Text
- Reasoning mode
- No
- Tool calling
- Yes
- Open weights
- Yes
- Cached input
- Not listed
Electricity per answer
GPU energy measured by AI Energy Score. Compare with other models
- Electricity, reasoning answer
- 0.27 Wh
What it would cost
At list price, without caching or batch discounts.
- 1,000 chat replies2K tokens in, 500 out each
- $0.73
- Summarise 100 long reports50K tokens in, 1K out each
- $0.56
- A coding agent’s working day20M tokens in, 1M out
- $2.90
Price history
Per 1M tokens, input then output. Tracked since 30 Sept 2026.
- 5 Nov 2026
- $0.10 → $0.09-10%$1.10 → $1.10
- 3 Nov 2026
- $0.09 → $0.10+11%$1.10 → $1.10
- 21 Oct 2026
- $0.10 → $0.09-10%$1.10 → $1.10
- 20 Oct 2026
- $0.09 → $0.10+11%$1.10 → $1.10
- 16 Oct 2026
- $0.10 → $0.09-10%$1.10 → $1.10
- 9 Oct 2026
- $0.09 → $0.10+11%$1.10 → $1.10
- 8 Oct 2026
- $0.15 → $0.09-40%$1.50 → $1.10-27%
- 8 Oct 2026
- $0.10 → $0.15+50%$1.10 → $1.50+36%
Alternatives at a similar price
From other labs, priced within about 40% of Qwen3 Next 80B A3B Instruct, with a comparable context window.
- Inkling 2 SmallThinking Machines, 1.05M context$0.30 in$1.00 out
- Mi:dm K 3.0 ProKt, 262K context$0.20 in$0.80 out
- Ripple 65B PreviewRicursiveai, 1.05M context$0.20 in$0.60 out
- Motif 3Motif Technologies, 262K context$0.30 in$1.20 out
- MiniMax M3.1 FlashMiniMax, 1.05M context$0.15 in$0.60 out
- DeepSeek V4.1 Flash 1017DeepSeek, 1.05M context$0.15 in$0.60 out