modelbenchmark.io

Qwen3.8 2.4T A95B

Alibaba · qwen3-8-2-4t-a95b

Compare

Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows

Specification

most-agreed values

Context
262K
Max output
131K
Released
2026-08-12
Knowledge cutoff
—
Retires
2026-11-04
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$2.00
Output
$6.00
Cache read
$0.20
Cache write
$2.50

Available from 25 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
iteracompute$1.95$5.70$0.25—1M131K—
aihubmix$2.00$6.00$0.50—262K131K—
aihubmix · aihubmix$2.00$6.00$0.50—1M131K—
deepinfra$2.00$6.00$0.20—262K
131K
262K
—
edenai$2.00$6.00$0.25$2.501M131K—
fireworks-ai · accounts$2.00$6.00$0.25—262K131K—
hyper$2.00$6.00$0.25—1M128K—
kilo$2.00$6.00$0.25$2.501M131K—
llmgateway$2.00$6.00$0.25—1M131K—
llmgateway-providers$2.00$6.00$0.25—
1M
1M
909K
131K
—
modal$2.00$6.00$0.25—1M131K—
novita-ai$2.00$6.00$0.25—1M131K—
openrouter$2.00$6.00$0.25—1M131K—
requesty$2.00$6.00$0.20—262K262K—
siliconflow$2.00$6.00$0.25—1M131K—
streamlake · streamlake$2.00$6.00$0.25$2.50984K128K—
together_ai$2.00$6.00$0.25—1M1M2026-11-04
vercel$2.00$6.00$0.25—262K128K—
cortecs$2.50$6.00$0.625—262K262K—
huggingface$2.50$6.25——262K131K—
merge-gateway$2.50$6.25$0.50—262K1M—
opper$2.50$6.00$0.63—262K131K—
tensorx$2.50$6.00$0.63—262K64K—
aimlapi$2.645$6.6125$0.529—262K52K—
chutes————00—

Price history

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

DateHostField$/M
2026-09-02openrouterCache read$0.20
2026-09-03openrouterCache read$0.25
2026-09-06openrouterCache read$0.25
2026-10-10openrouterCache read$0.25
2026-09-02together_aiCache read$0.50
2026-09-04together_aiCache read$0.25
2026-09-02openrouterInput$2.00
2026-09-06openrouterInput$2.00
2026-10-10openrouterInput$2.00
2026-09-02together_aiInput$2.50
2026-09-04together_aiInput$2.00
2026-09-02openrouterOutput$6.00
2026-09-06openrouterOutput$6.00
2026-10-10openrouterOutput$6.00
2026-09-02together_aiOutput$6.25
2026-09-04together_aiOutput$6.00
2026-09-17iteracomputeCache read$0.20
2026-10-16iteracomputeCache read$0.245
2026-10-22iteracomputeCache read$0.25
2026-09-17iteracomputeOutput$5.95
2026-10-16iteracomputeOutput$5.70
2026-09-23llmgateway-providersCache read$0.25
2026-09-24llmgateway-providersCache read$0.20
2026-10-12llmgateway-providersCache read$0.25
2026-10-13aimlapiCache read$0.6877
2026-10-23aimlapiCache read$0.529
2026-10-13aimlapiInput$3.4385
2026-10-23aimlapiInput$2.645
2026-10-13aimlapiOutput$8.5962
2026-10-23aimlapiOutput$6.6125

More from Alibaba

most-hosted first