Models/Qwen/Qwen3 Next 80B A3B Thinking

Qwen3 Next 80B A3B Thinking

Qwen · Open weights · Released Sep 11, 2025 · qwen/qwen3-next-80b-a3b-thinking
Best $0.15 in / $1.20 out via Alibaba · 131K ctx at this price (headline 262K)
CompareEstimate cost
262K contextToolsReasoningStructured outputOpen weights
Available from 2 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 17 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
PROVIDERINPUTOUTPUTCACHECONTEXTQUANTTTFTTPSUPTIME
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 17 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Recent changesRSS ↗
Aug 29, 2026endpoint removed · nebius3 → 2
About

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
Context window262,144
Max output32,768
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedSep 11, 2025
Knowledge cutoff2025-09-30
TokenizerQwen3
WeightsHugging Face ↗
Open weights
Hugging FaceQwen/Qwen3-Next-80B-A3B-Thinking ↗
Downloads41.9K
Likes496
Licenseapache-2.0
safetensors
Related
Qwen3.8 Max Prime$4.00 / $12.00Qwen3.8 Omni Flash$0.15 / $0.47Qwen3.8 Max (0902)$2.00 / $6.00Qwen3.8 Flash$0.15 / $0.47
Embed badge
Qwen3 Next 80B A3B Thinking price and speed badge
[![Qwen3 Next 80B A3B Thinking](https://modelindex.ai/badge/qwen/qwen3-next-80b-a3b-thinking)](https://modelindex.ai/models/qwen/qwen3-next-80b-a3b-thinking)
Sources
OpenRouter API23 minutes ago
AGGREGATOR
Hugging Face23 minutes ago
COMMUNITY
ModelIndex benchmarks20 days ago
MEASURED
Verified 23 minutes ago · list prices, not negotiated rates.