TokenDealHub
中文

Qwen: Qwen3.8 2.4T A95Bqwen

Bottom Line

Qwen: Qwen3.8 2.4T A95B: $2.00/1M input, $6.00/1M output, 1.0M context, CPS grade A. 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...

API Pricing (per 1M tokens)

Input$2.00
Output$6.00
Cache Read—
Cache Write—
Blended (3:1)$3.00

Specs & Performance

Context Length1.0M
Max Output909K
Intelligence40
Coding72
Math—
Speed39 tok/s
TTFT1.96s
CPS GradeA
Input / Output Modalitiestext → text

More from qwen

Qwen: Qwen3.8 Max
$2.00 / $6.00
Qwen: Qwen3.8 27B
$0.20 / $2.50
Qwen: Qwen3 Max Thinking
$0.78 / $3.90
Qwen: Qwen3.7 Max
$1.48 / $4.42
Qwen: Qwen3 VL 30B A3B Instruct
$0.15 / $0.60
Qwen: Qwen3 Next 80B A3B Instruct
$0.09 / $1.10

Looking for cheaper alternatives?

Find the cheapest model by task, or compare two models head-to-head.

Cheapest by task →Compare two models →Compare all models →

FAQ

How much does the Qwen: Qwen3.8 2.4T A95B API cost?

Qwen: Qwen3.8 2.4T A95B costs $2.00/1M input tokens and $6.00/1M output tokens. Blended cost at a 3:1 ratio is about $3.00/1M tokens.

What is the context window of Qwen: Qwen3.8 2.4T A95B?

Qwen: Qwen3.8 2.4T A95B supports a 1.0M token context window with up to 909K output tokens.

Is Qwen: Qwen3.8 2.4T A95B worth it?

Qwen: Qwen3.8 2.4T A95B has a CPS grade of A (score 67), intelligence index 40, coding index 72. Use the compare page to benchmark against rivals.