Alibaba (Qwen)

Qwen3.5 Flash

Type
language model
Context
1,000K tokens
Max output
66K
Released
24 February 2026
Knowledge cutoff
January 2025
API string
qwen3.5-flash

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
NanoGPT $0.09 $0.36 31 Jul 2026
Vercel $0.1 $0.4 31 Jul 2026
ZenMux $0.1 $0.4 31 Jul 2026
alibaba-cn $0.172 $1.72 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 1,413.61 1,408–1,419 — —
Arena Score, expert questions 1,411.36 1,402–1,420 — —
Arena Score in French 1,409.81 1,395–1,425 — —
Arena Score, mathematics 1,409.11 1,398–1,420 — —
Arena Score in English 1,405.65 1,401–1,411 — —
Arena Score, hard prompts 1,404.13 1,400–1,409 — —
Arena Score in Spanish 1,399.29 1,384–1,415 — —
Arena Score, overall 1,397.75 1,394–1,402 — —
Arena Score, long queries 1,393.08 1,388–1,398 — —
Arena Score, multi-turn dialogue 1,392.8 1,386–1,400 — —
Arena Score in Russian 1,383.64 1,375–1,392 — —
Arena Score, instruction following 1,375.08 1,370–1,381 — —
Arena Score, creative writing 1,342.67 1,335–1,350 — —
Arena Score, web development 1,237.96 1,218–1,258 — —
Mock AIME 2024–2025 — olympiad problems 85.54 % · with a tuned harness Epoch evaluations
GPQA Diamond — graduate-level questions 78.45 % · with a tuned harness Epoch evaluations
SimpleQA Verified — factual accuracy 19.76 % — Epoch evaluations
Chess puzzles 15.83 % — Epoch evaluations