Alibaba (Qwen)

Qwen3.6 Plus

Type
language model
Context
1,000K tokens
Max output
66K
Released
2 April 2026
API string
qwen/qwen3.6-plus
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Merge Gateway $0.276 $1.651 31 Jul 2026
AIHubMix $0.28 $1.69 31 Jul 2026
CrossModel $0.32 $1.88 31 Jul 2026
Kilo Code $0.325 $1.95 31 Jul 2026
OpenRouter $0.325 $1.95 31 Jul 2026
Pioneer $0.325 $1.95 31 Jul 2026
opencode-go $0.5 $3 31 Jul 2026
alibaba-cn $0.5 $3 31 Jul 2026
Alibaba (Qwen) $0.5 $3 31 Jul 2026
EmpirioLabs AI $0.5 $3 31 Jul 2026
LLM Gateway $0.5 $3 31 Jul 2026
OpenCode Zen $0.5 $3 31 Jul 2026
OrcaRouter $0.5 $3 31 Jul 2026
Together AI $0.5 $3 31 Jul 2026
Vercel $0.5 $3 31 Jul 2026
ZenMux $0.5 $3 31 Jul 2026
hyper $2 $6 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.

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, programming 1,465.74 1,459–1,472
Arena Score, web development 1,457.86 1,452–1,464
Arena Score, expert questions 1,457.59 1,448–1,467
Arena Score, mathematics 1,450.87 1,439–1,463
Arena Score in French 1,450.58 1,434–1,467
Arena Score, hard prompts 1,448.32 1,443–1,453
Arena Score in English 1,445.67 1,440–1,451
Arena Score, multi-turn dialogue 1,440.5 1,433–1,448
Arena Score, long queries 1,439.21 1,433–1,445
Arena Score, overall 1,436.76 1,433–1,441
Arena Score in Russian 1,435.31 1,426–1,445
Arena Score in Spanish 1,432.89 1,416–1,450
Arena Score, instruction following 1,424.94 1,419–1,431
Arena Score, creative writing 1,403.57 1,395–1,412
Mock AIME 2024–2025 — olympiad problems 90.55 % · with a tuned harness Epoch evaluations
GPQA Diamond — graduate-level questions 83.17 % · with a tuned harness Epoch evaluations
SWE-bench Verified — fixing bugs in repositories 57.85 % · with a tuned harness Epoch evaluations
SimpleQA Verified — factual accuracy 49.1 % Epoch evaluations
Chess puzzles 11.79 % Epoch evaluations
CritPt — physics problems 2.86 %