← Model list

Qwen3.8 2.4T A95B

alibaba·alibaba/qwen3.8-2.4t-a95b·GA·Open weights·qwen series·NEW

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

At a glance
Reference price$2.50 / $6.25 per 1M
Cache read $0.50 · Merge Gateway
Lowest paid$1.80 / $5.40
Requesty Gateway · 1.4× spread
Context262,144
⚠ Providers report 262,144–1,048,576; the table below is authoritative
Output limit1,010,000
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideo
Knowledge cutoff
Released / updated2026-08-12 / 2026-08-12

Quality & performanceArtificial Analysis · Intelligence Index v4.1

Intelligence57.7
Value21
Coding71.9
Agentic57.1
Output speed46 tok/s
TTFT2.65 s
Cost per task$1.0919
Value formulaIQ 57.7 ÷ min blended $2.700 = 21

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 10 providers10 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Requesty
qwen3.8-2.4T-A95B
Gateway$1.80$5.40$0.18262,144262,144
Deep Infra
Qwen/Qwen3.8-2.4T-A95B
Cloud$2.00$6.00$0.20262,144131,072
OpenRouterGateway$2.00$6.00$0.251,048,576262,144
DigitalOcean
qwen3.8-max
Cloud$2.00$6.00$0.20262,144262,144
Vercel AI GatewayCloud$2.00$6.00$0.20262,144131,072
Eden AIGateway$2.00$6.00$0.25$2.501,000,000131,072
Kilo GatewayGateway$2.00$6.00$0.25$2.501,000,000262,144
CortecsGateway$2.50$6.00$0.625262,144262,144
Hugging Face
Qwen/Qwen3.8-2.4T-A95B
Cloud$2.50$6.25262,144131,072
Merge GatewayGateway$2.50$6.25$0.50262,1441,010,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Requesty$435.60
2Deep Infra$484.00
3DigitalOcean$484.00
4Vercel AI Gateway$484.00
5OpenRouter$490.00
6Eden AI$490.00
The cheapest paid channel is the only channel.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

effort = noneeffort = loweffort = mediumeffort = higheffort = maxbudget_tokenseffort = xhigh

1 / 10 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$6.25$02026-08-132026-08-212026-08-13 · Input list $2.002026-08-15 · Input list $2.502026-08-17 · Input list $2.502026-08-21 · Input list $2.502026-08-13 · Output list $6.002026-08-15 · Output list $6.002026-08-17 · Output list $6.252026-08-21 · Output list $6.252026-08-13 · Min blended $3.002026-08-15 · Min blended $3.002026-08-17 · Min blended $3.002026-08-21 · Min blended $2.70