Qwen: Qwen3.8 2.4T A95B

qwen/qwen3.8-2.4t-a95b

Qwen3.8 2.4T A95B is Qwen's open-weight contender, ranking #34 of 248 on the TryAii Score. It's strongest on knowledge (#10 on GPQA). API pricing starts at $2/$6 per million input/output tokens — about the going rate for its score class, with 8 independent hosts serving it. It's reasonably quick at roughly 37-89 tokens/sec.

Prompt $/1M

$2.000

Completion $/1M

$6.000

Context

1,048,576 tok

Best provider

166 tok/s · Together

Specs

Model id: qwen/qwen3.8-2.4t-a95b
Display name: Qwen: Qwen3.8 2.4T A95B
Modality: text->text
Tokenizer: Qwen
Instruct type: —
Context length: 1,048,576
Max completion: 131,072
Prompt $/1M: $2.000
Completion $/1M: $6.000
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionno
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Togetherfastest	166	482 ms	558 ms
Modal	144	630 ms	821 ms
DeepInfra	91	767 ms	1,693 ms
Venice	84	3,277 ms	4,896 ms
Fireworks	47	1,393 ms	2,187 ms
Alibaba	41	1,903 ms	2,132 ms
Artificial Analysis	38	1,948 ms	—
SiliconFlow	37	1,234 ms	1,576 ms
Novita	33	4,527 ms	5,751 ms
DigitalOcean	17	2,718 ms	3,629 ms
qwenfastest	—	—	—