Qwen3 Next 80B A3B Instruct
Qwen · Open weights · Released Sep 11, 2025 · qwen/qwen3-next-80b-a3b-instruct
262K contextToolsStructured outputPrompt cachingOpen weights
Available from 5 providersUSD / MTOK · VERIFIED 4 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 DeepInfra | $0.09 | $1.10 | — | 262K | fp8 | 0.58s | 104 tok/s | 99.5% |
 Alibaba | $0.098 | $0.78 | — | 131K | — | 1.2s | 116 tok/s | 100.0% |
 Parasail | $0.10 | $1.10 | $0.07 | 262K | fp8 | 0.7s | 201 tok/s | 100.0% |
 Google | $0.15 | $1.20 | — | 262K | — | 0.61s | 99 tok/s | 100.0% |
 Novita | $0.15 | $1.50 | — | 131K | bf16 | 1.6s | 161 tok/s | 99.8% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 43 hours ago
About
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...
Specifications
Context window262,144
Max output262,144
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedSep 11, 2025
Knowledge cutoff2025-09-30
TokenizerQwen3
WeightsHugging Face ↗
Open weights
safetensors
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3-next-80b-a3b-instruct)Sources
OpenRouter API4 minutes ago
AGGREGATORHugging Face4 minutes ago
COMMUNITYModelIndex benchmarks43 hours ago
MEASUREDVerified 4 minutes ago · list prices, not negotiated rates.