Alibaba (Qwen)

Qwen QwQ 32B Preview

Type
language model
Context
33K tokens
Max output
33K
Released
27 February 2025
API string
qwen/qwq-32b-preview

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
NanoGPT $0.2 $0.2 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, mathematics 1,213.52 1,189–1,238 — —
Arena Score in English 1,184.45 1,170–1,199 — —
Arena Score, long queries 1,167.03 1,141–1,193 — —
Arena Score, hard prompts 1,162.87 1,144–1,182 — —
Arena Score, overall 1,161.96 1,151–1,173 — —
Arena Score, instruction following 1,156.39 1,141–1,172 — —
Arena Score, programming 1,155.71 1,132–1,179 — —
Arena Score, multi-turn dialogue 1,140.73 1,114–1,168 — —
Arena Score, creative writing 1,134.13 1,106–1,162 — —
Arena Score, expert questions 1,134.07 1,098–1,170 — —
Arena Score in Russian 1,113.61 1,087–1,140 — —