Qwen3.8 2.4t A95B

qwen3.8-2.4t-a95b · Qwen

Qwen3.8-2.4T-A95B is Alibaba’s most powerful Qwen model to date. It is a 2.4‑trillion‑parameter sparse Mixture-of-Experts (MoE) model with approximately 95 billion active parameters. It is built for autonomous, long‑duration tasks: multi‑day code runs, reproducing research papers, and self‑improvement.

API Pricing

Input$2 / 1M tokens
Output$6 / 1M tokens
Cache read$0.5 / 1M tokens

Specifications

Context1M tokens
Modalitiestext
CapabilitiesThinking, Tool calling, Web search, Code interpreter, Structured outputs, Prompt caching

Frequently asked questions

What is Qwen3.8 2.4t A95B?

Qwen3.8-2.4T-A95B is Alibaba’s most powerful Qwen model to date. It is a 2.4‑trillion‑parameter sparse Mixture-of-Experts (MoE) model with approximately 95 billion active parameters. It is built for autonomous, long‑duration tasks: multi‑day code runs, reproducing research papers, and self‑improvement.

What is the context length of Qwen3.8 2.4t A95B?

Qwen3.8 2.4t A95B has a 1,000,000 token context window.

How much does Qwen3.8 2.4t A95B cost?

On AIHubMix, Qwen3.8 2.4t A95B costs $2 per million input tokens and $6 per million output tokens. Cached input reads are billed at $0.5 per million tokens.

What modalities does Qwen3.8 2.4t A95B support?

Qwen3.8 2.4t A95B accepts text input.

What capabilities does Qwen3.8 2.4t A95B support?

Qwen3.8 2.4t A95B supports tool calling, function calling, structured outputs, web search, long context and thinking. Per-protocol parameter support is listed in the capability table on this page.

How do I call Qwen3.8 2.4t A95B via API?

Qwen3.8 2.4t A95B is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to qwen3.8-2.4t-a95b — no other code changes needed.

Who created Qwen3.8 2.4t A95B?

Qwen3.8 2.4t A95B is developed by Qwen. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

When was Qwen3.8 2.4t A95B released?

Qwen3.8 2.4t A95B was released on August 12, 2026 by Qwen.

More models from Qwen

See all Qwen models →

Qwen3.8 Omni Flash

by Qwen

Qwen3.8 Omni Flash is Alibaba Cloud Qwen's next-generation native multimodal model…

$0.1126/1M in · $0.38/1M out
1,000,000 tokens context

Decision Model Preview

by Qwen

Alibaba Cloud has launched the decision model decision-model-preview. This structured…

64,000 tokens context

Qwen 3.8 27B

by Qwen

Qwen3.8-27b is an Alibaba-released dense vision-language model with open-source weights…

$1.1/1M in · $1.65/1M out
131,072 tokens context

Qwen3.8 Max 2026 09-02

by Qwen

Qwen3.8-Max-0902 (also known as qwen3.8-max-2026-09-02) is a snapshot version of Alibaba…

$1.69/1M in · $5.07/1M out
1,000,000 tokens context

Qwen3.8 Flash

by Qwen

Qwen3.8 Flash is Alibaba Cloud Qwen’s flagship native vision-language model for coding…

$0.1126/1M in · $0.38/1M out
1,000,000 tokens context

Wan3.0 Video

by Qwen

Wan 3.0 (Tongyi Wanxiang 3.0) is an integrated video generation and editing model…

$2/1M in · $2/1M out

Use Qwen3.8 2.4t A95B via the AIHubMix unified API — one interface for every major LLM.