Qwen3 Next 80B A3B Thinking pricing & benchmarks
Qwen3 Next 80B A3B Thinking is available from Alibaba at $0.150 per million input tokens and $1.20 per million output tokens ($0.412 blended at 3:1). It accepts up to 262,144 tokens of context. 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..…
Pricing
Per million tokens · OpenRouter
Input$0.150
Output$1.20
Blended (3:1)$0.412
Specification
qwen/qwen3-next-80b-a3b-thinking
Context window262K
Max output262K
ReleasedSep 2025
LicenceOpen weights
Modalitiesin:text, out:text
No independently-run benchmark scores are published for Qwen3 Next 80B A3B Thinking yet. We show nothing rather than reprinting an unverified figure.
Where to run Qwen3 Next 80B A3B Thinking
3 hosts · all priced within ~5% of each other. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| Google (global) | $0.412 | $0.150 / $1.20 | 262K | — | 100.0% |
| Nebius ⚠ 128K context, not 262K |
$0.412 | $0.150 / $1.20 | 128K | fp8 | 99.9% |
| Alibaba ⚠ 131K context, not 262K |
$0.412 | $0.150 / $1.20 | 131K | fp8 | 99.8% |
Host prices and uptime from OpenRouter, synced 2026-08-08. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Qwen3 Next 80B A3B Thinking
Qwen3 Next 80B A3B Thinking vs DeepSeek V4 Flash 0731
Qwen3 Next 80B A3B Thinking vs Claude Opus 5
Qwen3 Next 80B A3B Thinking vs Gemini 3.6 Flash
Qwen3 Next 80B A3B Thinking vs Kimi K3
Qwen3 Next 80B A3B Thinking vs GPT-5.6 Luna
Qwen3 Next 80B A3B Thinking vs GPT-5.6 Terra
Qwen3 Next 80B A3B Thinking vs GPT-5.6 Sol
Qwen3 Next 80B A3B Thinking vs Grok 4.5
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 on OpenRouter. At a 3:1 input:output mix that blends to $0.412 per million tokens.
What is Qwen3 Next 80B A3B Thinking's context window?
Qwen3 Next 80B A3B Thinking accepts up to 262,144 tokens of context, and can generate up to 262,144 output tokens.