Qwen3.8 2.4T A95B pricing & specs

Alibaba (Qwen) · released 2026-08-12 · ● verified 2026-10-11

input / 1M$2.00via DeepInfra
output / 1M$6.00via DeepInfra
context262.1K
max output131.1K

// price history ($/1M tokens)

$6.90
input $/1Moutput $/1M2026-08-12 → 2026-10-11

// cheaper or similar alternatives

modelinoutctxvs Qwen3.8 2.4T A95B
Gemma 4 E2B IT$0.04$0.08131.1K−98.3%
Qwen3.7 Flash$0.03$0.131M−98.2%
Qwen Turbo$0.05$0.201M−97.1%
DeepSeek V4 Flash 0731$0.06$0.181.05M−97%
GPT OSS 120B$0.05$0.25131.1K−96.7%

// price by host

hostin $/1Mout $/1M
DeepInfra$2.00$6.00
Fireworks AI$2.00$6.00
Novita AI$2.00$6.00

// faq

How much does Qwen3.8 2.4T A95B cost?

Qwen3.8 2.4T A95B costs $2.00 per million input tokens and $6.00 per million output tokens (cheapest tracked host: DeepInfra). At 50M input and 10M output tokens per month that is about $160.

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

262.1K tokens, with up to 131.1K output tokens per request.

Does Qwen3.8 2.4T A95B support prompt caching?

Yes. Cached input tokens cost $0.20 per million.

What are cheaper alternatives to Qwen3.8 2.4T A95B?

Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Qwen Turbo ($0.05 in / $0.20 out) offer the same input types and capabilities for less.

Is Qwen3.8 2.4T A95B open weights?

Yes. It is available from 3 tracked hosts; the cheapest is DeepInfra at $2.00 input and $6.00 output per million tokens.

// spec sheet

input / 1M
$2.00
output / 1M
$6.00
cache read / 1M
$0.20
blended (3:1)
$3.00
context
262.1K
max output
131.1K
input types
text
reasoning
yes
tool calling
yes
structured output
yes
open weights
yes
knowledge cutoff
n/a
price source
DeepInfra

report a data error

// cost calculator

modelin $/1Mout $/1M= monthly
Gemma 4 E2B IT$0.04$0.08$2.80
Qwen3.7 Flash$0.03$0.13$2.80
Qwen Turbo$0.05$0.20$4.50
Qwen3.8 2.4T A95B$2.00$6.00$160

Base-tier list prices. Long-context tiers, caching and batch discounts are not included.