modelbenchmark.io

Qwen3 32B

Alibaba · qwen3-32b

Compare

Dense open Qwen model for self-hosted chat, reasoning, and coding

Specification

alibaba listing

Context
131K
Max output
16K
Released
2025-04
Knowledge cutoff
2025-04
Retires
2026-07-17
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · alibaba list price

Input
$0.70
Output
$2.80
Cache read
$0.05
Cache write
$0.90

Available from 26 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
alibabavendor$0.70$2.80131K16K
iflowcnfreefree128K32K
deepinfra$0.08$0.2841K
16K
41K
kilo$0.08$0.2841K16K
openrouter$0.08$0.28131K16K
ovhcloud · ovhcloud$0.08$0.2332K32K
cortecs$0.089$0.31232K32K
abacus$0.09$0.29131K8K
ovhcloud$0.09$0.2533K33K
nano-gpt$0.10$0.30$0.0541K33K
nebius$0.10$0.3041K41K
siliconflow$0.14$0.57131K131K
siliconflow-cn$0.14$0.57131K131K
amazon-bedrock$0.15$0.6033K16K
bedrock_converse$0.15$0.60131K16K
merge-gateway$0.15$0.60131K33K
alibaba-cn$0.287$1.147131K16K
groq$0.29$0.59131K131K2026-07-17
helicone$0.29$0.59131K41K
huggingface$0.29$0.59131K16K
llmgateway$0.36$0.8741K16K
llmgateway-providers · scx-ai$0.36$0.8733K8K
sambanova · sambanova$0.40$0.808K8K2026-04-06
fireworks_ai$0.90$0.90131K131K
pioneer$0.90$0.90$0.90$0.90131K8K
qiniu-ai40K4K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02cortecsInput$0.099
2026-09-05cortecsInput$0.089
2026-09-02nebiusInput$0.10
2026-09-03nebiusInput$0.10
2026-09-02openrouterInput$0.08
2026-09-06openrouterInput$0.08
2026-09-02cortecsOutput$0.299
2026-09-05cortecsOutput$0.312
2026-09-02nebiusOutput$0.30
2026-09-03nebiusOutput$0.30
2026-09-02openrouterOutput$0.28
2026-09-06openrouterOutput$0.28

Other listings of this model

same model, different key

More from Alibaba

most-hosted first