RentGPU RentGPU
Find a GPU →
by Alibaba (Qwen Team)

Qwen: Qwen3.8 2.4T A95B.

text closed 1M ctx
Cheapest input
$2.0/M
on DeepInfra
Cheapest output
$6.0/M
on DeepInfra
Hosted equiv.
~$2.16/hr
@ 100 tok/s on DeepInfra

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

Hosted API only

No self-host path — closed weights.

Qwen: Qwen3.8 2.4T A95B's weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
DeepInfra hosted inference $2.0 $6.0 Launch ↗
OpenRouter api aggregator $2.0 $6.0 Launch ↗
Together AI hosted inference $2.5 $6.25 Launch ↗
FAQ

Frequently asked.

How do I run Qwen: Qwen3.8 2.4T A95B?
Qwen: Qwen3.8 2.4T A95B is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access Qwen: Qwen3.8 2.4T A95B?
Qwen: Qwen3.8 2.4T A95B is available via Together AI, DeepInfra, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Qwen: Qwen3.8 2.4T A95B?
API pricing starts at $2.0/M input tokens and $6.0/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Qwen: Qwen3.8 2.4T A95B open-source or proprietary?
Qwen: Qwen3.8 2.4T A95B is a proprietary model from Alibaba (Qwen Team). Access is API-only — there are no public weights to download.