Patchwire

Qwen · Released Sep 11, 2025

Qwen3 Next 80B A3B Instruct

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…

Open weights
Compare in showdown → OpenRouter ↗ All Qwen models
Released
Sep 11 2025
Context window
262K 16K out
Input / 1M tokens
$0.09 from $0.072
Output / 1M tokens
$1.10 from $0.88

Where to run it

3 providers compared

Cheapest: DeepInfra at $0.072 / $0.88 per 1M input / output tokens — 47% less than the priciest option.

ProviderInputOutputCache readContextMax outputUptimevs. best
DeepInfraFP8 $0.072 $0.88 —262K236K— Cheapest
DeepInfraFP8 $0.09 $1.10 —262K16K99.6%24h +25%
ParasailFP8 $0.10 $1.10 $0.07262K236K98.4%24h +28%
Googleglobal $0.15 $1.20 —262K236K99.8%24h +51%
DeepInfrapriority · FP8 $0.14 $1.65 —262K236K100%24h +87%

Value

Price vs. performance

2 models score higher for the same price or lesson Fiction.LiveBench, e.g. Qwen3 32B.
40.6%59.5%78.3%97.2% $0.01$0.10$1.00$10.00$100.00 Kimi K2.5 (Moonshot AI) — 86.1% · $0.50/1M in DeepSeek V3.2 (DeepSeek) — 83.3% · $0.28/1M in DeepSeek V3.2 Exp (DeepSeek) — 83.3% · $0.27/1M in GPT-5 (OpenAI) — 97.2% · $1.25/1M in GPT-5 Mini (OpenAI) — 69.4% · $0.25/1M in GPT-5 Nano (OpenAI) — 44.4% · $0.05/1M in gpt-oss-120b (OpenAI) — 44.4% · $0.15/1M in o3 Pro (OpenAI) — 97.2% · $20.00/1M in R1 0528 (DeepSeek) — 75.0% · $0.50/1M in Qwen3 235B A22B Thinking 2507 (Qwen) — 75.0% · $0.45/1M in Qwen3 235B A22B Instruct 2507 (Qwen) — 67.7% · $0.09/1M in Qwen3 30B A3B (Qwen) — 40.6% · $0.12/1M in Qwen3 14B (Qwen) — 62.5% · $0.12/1M in Qwen3 32B (Qwen) — 74.2% · $0.08/1M in Qwen3 Next 80B A3B Instruct (Qwen) — 55.6% · $0.09/1M in Qwen3 Next 80B A3B Instruct

Qwen3 Next 80B A3B Instruct Other Qwen Other labs Value frontier · Fiction.LiveBench vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.

Benchmarks

1 benchmark score

BenchmarkScoreRankLeader
Fiction.LiveBenchWriting & content · Understanding long creative writing (16k tokens) 55.6% #12of 15 GPT-597.2%

Specs

Details

Model ID
qwen/qwen3-next-80b-a3b-instruct
Developer
Qwen
Release date
Sep 11, 2025 ·
Context window
262,144 tokens
Max output
16,384 tokens
API price
$0.09 / $1.10 per 1M input / output tokens
Providers
3
Input types
text
Reasoning
No
Tool calling
Yes
Open weights
Yes
Free tier
No

Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. Uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.