Qwen3.8 2.4T A95B

Open-weight sparse MoE variant of Qwen3.8 Max with 95B active out of 2.4T total parameters.

qwen3.8-2.4t-a95b
STABLEGet StartedView uptime
1,010,000 context
Released August 12, 2026
Starting at $2.00/M input tokens
Starting at $6.00/M output tokens
Streaming
Tools
Reasoning
JSON Output
Structured JSON
No ratings yetSign in to rate

All Providers for Qwen3.8 2.4T A95B

PassingRight routes requests to the best providers that are able to handle your prompt size and parameters.

Context: 1.0M
Input
$2
/M tokens
Cache Read
$0.25
/M tokens
Output
$6
/M tokens
Get Started
Context: 262.1kQuant: fp4
Input
$2
/M tokens
Cache Read
$0.2
/M tokens
Output
$6
/M tokens
Get Started
Context: 1M
Input
$2
/M tokens
Cache Read
$0.25
/M tokens
Output
$6
/M tokens
Get Started

Frequently asked questions

What is Qwen3.8 2.4T A95B?

Open-weight sparse MoE variant of Qwen3.8 Max with 95B active out of 2.4T total parameters. You can access it through PassingRight's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does Qwen3.8 2.4T A95B cost?

Pricing for Qwen3.8 2.4T A95B on PassingRight starts at $2.00 per million input tokens and $6.00 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

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

Qwen3.8 2.4T A95B supports a context window of up to 1,010,000 tokens on its largest provider deployment.

Which providers serve Qwen3.8 2.4T A95B?

Qwen3.8 2.4T A95B is served by Together AI, DeepInfra, NovitaAI through PassingRight. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does Qwen3.8 2.4T A95B support tool calling and structured outputs?

Yes. Qwen3.8 2.4T A95B supports both tool (function) calling and strict JSON output schema (upstream-enforced) through PassingRight.

When was Qwen3.8 2.4T A95B released?

Qwen3.8 2.4T A95B was released on August 12, 2026.