Alibaba (Qwen)

Qwen3 Next 80B A3B Instruct

Type
language model
Context
262K tokens
Max output
16K
Released
1 December 2024
API string
qwen/qwen3-next-80b-a3b-instruct
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
DeepInfra Qwen/Qwen3-Next-80B-A3B-Instruct $0.09 $1.1 31 Jul 2026
Kilo Code $0.09 $1.1 31 Jul 2026
OpenRouter $0.1 $1.1 31 Jul 2026
io.net $0.1 $0.8 31 Jul 2026
hyper $0.118 $1.136 31 Jul 2026
DeepInfra deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct $0.14 $1.4 31 Jul 2026
Helicone $0.14 $1.4 31 Jul 2026
alibaba-cn $0.144 $0.574 31 Jul 2026
Merge Gateway $0.144 $0.574 31 Jul 2026
neon $0.15 $1.2 31 Jul 2026
novita-ai $0.15 $1.5 31 Jul 2026
Alibaba (Qwen) dashscope/qwen3-next-80b-a3b-instruct $0.15 $1.2 31 Jul 2026
Google Vertex AI $0.15 $1.2 31 Jul 2026
Jiekou.AI $0.15 $1.5 31 Jul 2026
LLM Gateway $0.15 $1.2 31 Jul 2026
NanoGPT $0.15 $0.65 31 Jul 2026
Novita AI $0.15 $1.5 31 Jul 2026
Together AI $0.15 $1.5 31 Jul 2026
Vercel $0.15 $1.2 31 Jul 2026
Hugging Face $0.25 $1 31 Jul 2026
Alibaba (Qwen) qwen3-next-80b-a3b-instruct $0.5 $2 31 Jul 2026
Fireworks AI $0.9 $0.9 31 Jul 2026

Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.

A single provider appears several times if it sells this model under different identifiers and at different prices — for example, at different weight precision. The identifier is shown next to the name. Identical offers that arrived from two sources under different spellings are merged into one row.

The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.

Measurement results

Task set Result Run conditions Measured by
Arena Score in Spanish 1,449.16 1,424–1,474
Arena Score, mathematics 1,442.26 1,426–1,459
Arena Score, programming 1,441.15 1,433–1,450
Arena Score, hard prompts 1,428.36 1,422–1,434
Arena Score in English 1,425.02 1,419–1,431
Arena Score, overall 1,418.72 1,414–1,423
Arena Score, multi-turn dialogue 1,417.95 1,409–1,427
Arena Score in French 1,416.22 1,384–1,448
Arena Score, expert questions 1,410.5 1,392–1,429
Arena Score, long queries 1,402.59 1,394–1,411
Arena Score in Russian 1,400.45 1,384–1,417
Arena Score, instruction following 1,389.51 1,382–1,397
Arena Score, creative writing 1,334.6 1,324–1,345