qwen Open weights Reasoning

Qwen3 Next 80B A3B Thinking pricing & benchmarks

Released Sep 11, 2025 · served by 3 providers

Input / 1M tokens$0.098
Output / 1M tokens$0.780
Context window262K
Cached input
Intelligence index16.7
Coding index17.4
Agentic index2.1
1M in + 300K out$0.33

What Qwen3 Next 80B A3B Thinking is

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...

Providers and prices for Qwen3 Next 80B A3B Thinking

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Alibabacheapest $0.098 $0.780 131K 99.3%
Google $0.150 $1.20 262K 100.0%
Nebius $0.150 $1.20 128K fp8 99.9%

Cheaper models in the same class

Models scoring within 4 points of Qwen3 Next 80B A3B Thinking on the Intelligence Index, but with a lower output price.

FAQ

How much does the Qwen3 Next 80B A3B Thinking API cost?

$0.098 per 1M input tokens and $0.780 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.33.

Is Qwen3 Next 80B A3B Thinking free?

No. It is a paid model starting at $0.098 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Qwen3 Next 80B A3B Thinking?

Alibaba at $0.098 input / $0.780 output per 1M tokens.

Can I self-host Qwen3 Next 80B A3B Thinking?

Yes — weights are published as Qwen/Qwen3-Next-80B-A3B-Thinking on Hugging Face, so you can run it on your own hardware.