Alibaba (Qwen)

Qwen2.5 Coder 32b Instruct

Type
language model
Context
128K tokens
Max output
4K
Released
6 November 2024
API string
qwen/qwen2.5-coder-32b-instruct
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Nscale $0.06 $0.2 31 Jul 2026
Hyperbolic $0.12 $0.3 31 Jul 2026
NanoGPT $0.201 $0.201 31 Jul 2026
alibaba-cn $0.287 $0.861 31 Jul 2026
cloudflare-workers-ai $0.66 $1 31 Jul 2026
Cloudflare AI Gateway $0.66 $1 31 Jul 2026
Cloudflare Workers AI $0.66 $1 31 Jul 2026
OVHCloud AI Endpoints $0.87 $0.87 31 Jul 2026
Fireworks AI $0.9 $0.9 1 Aug 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 1,276.12 1,258–1,294 — —
Arena Score, hard prompts 1,251.58 1,237–1,266 — —
Arena Score, long queries 1,251.03 1,232–1,270 — —
Arena Score, mathematics 1,250.58 1,231–1,270 — —
Arena Score in English 1,248.1 1,237–1,259 — —
Arena Score, overall 1,230.21 1,222–1,238 — —
Arena Score in Russian 1,227.22 1,209–1,246 — —
Arena Score, instruction following 1,223.26 1,211–1,235 — —
Arena Score, multi-turn dialogue 1,222.37 1,205–1,240 — —
Arena Score, expert questions 1,220.12 1,187–1,253 — —
Arena Score, creative writing 1,174.29 1,155–1,193 — —