modelbenchmark.io

Qwen3 235B A22B Instruct 2507

Alibaba · qwen3-235b-a22b-instruct

Compare

Qwen3 235B MoE instruct model for long-context multilingual chat and reasoning

Specification

most-agreed values

Context
262K
Max output
16K
Released
2025-07-21
Knowledge cutoff
2025-04
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.20
Output
$0.60
Cache read
$0.065
Cache write
$1.20

Available from 30 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
iflowcnfreefree256K64K
modelscopefreefree262K131K
cortecs$0.069$0.455$0.018262K262K
deepinfra$0.09$0.55262K
16K
262K
llmgateway$0.09$0.58262K8K
llmgateway-providers
$0.09
$0.60
$0.58
$1.20
131K
262K
16K
8K
meganova$0.09$0.60262K262K
novita$0.09$0.58131K16K
novita-ai$0.09$0.58131K16K
merge-gateway$0.10$0.60$0.05131K33K
wandb · wandb$0.10$0.10262K262K
abacus$0.13$0.60262K8K
nano-gpt$0.13$0.50$0.065262K16K
jiekou$0.15$0.80131K16K
venice$0.15$0.75128K16K
nebius$0.20$0.60262K
8K
262K
submodel$0.20$0.30262K131K
crusoe$0.22$0.80$0.11262K16K
fireworks_ai$0.22$0.88262K262K
llmgateway-providers · vertex-openai$0.22$0.88262K33K
edenai$0.23$0.92131K16K
replicate · replicate$0.264$1.06
302ai$0.29$1.143128K66K
scaleway$0.75$2.25260K16K
scaleway · scaleway$0.75$2.25256K16K
huggingface$0.855$2.565262K16K
greenpt$1.026$3.078262K16K
pioneer$1.20$1.20$1.20$1.20262K131K
crusoe · crusoe$3.00$3.00262K262K
qiniu-ai262K64K

Price history

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

DateHostField$/M
2026-09-02nebiusInput$0.20
2026-09-06nebiusInput$0.20
2026-09-02nebiusOutput$0.60
2026-09-06nebiusOutput$0.60

Other listings of this model

same model, different key

More from Alibaba

most-hosted first