Qwen: Qwen3.8 2.4T A95B

qwen/qwen3.8-2.4t-a95b

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, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.

Model specifications

Input
text
Output
text
Context
262,144 tokens
Max output
131,100 tokens
Input price
/ 1M tokens
Output price
$3 / 1M tokens
Released
2026-08-13

Capabilities

  • Streaming
  • Function calling
  • Vision
  • JSON mode

Provider pricing, discounts and data privacy

Compare effective provider prices, published discounts, regions, retention policies, training use, compliance, and privacy links by service tier.

Standard service tier

3 available providers · discounts up to 50% · tier input average .6 / 1M tokens · tier output average $4.8 / 1M tokens

Alibaba Cloud Int.(SG)

Tier: Standard · Region: SG

Pricing
Input
/ 1M tokens
Output
$3 / 1M tokens
Cache read
$0.125 / 1M tokens
Discounts
  • Input: 50% off — list $2 / 1M tokens, discounted / 1M tokens, effective / 1M tokens
  • Cache read: 50% off — list $0.25 / 1M tokens, discounted $0.125 / 1M tokens, effective $0.125 / 1M tokens
  • Output: 50% off — list $6 / 1M tokens, discounted $3 / 1M tokens, effective $3 / 1M tokens
Data privacy and compliance
Region
SG
Zero data retention
Yes
Data retention
30-day retention
Used for training
No
Data collection
Moderated
No
GDPR compliant
Yes
HIPAA compliant
No
SOC 2 certified
Yes
BYOK supported
Yes

Privacy policy · Terms · Official website · Documentation · Status · Support

DeepInfra

Tier: Standard · Region: US

Pricing
Input
.8 / 1M tokens
Output
$5.4 / 1M tokens
Cache read
$0.18 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Region
US
Zero data retention
Yes
Data retention
Zero retention
Used for training
No
Data collection
Moderated
No
GDPR compliant
Yes
HIPAA compliant
No
SOC 2 certified
Yes
BYOK supported
Yes

Privacy policy · Terms · Official website · Documentation · Status · Support

Fireworks

Tier: Standard · Region: US

Pricing
Input
$2 / 1M tokens
Output
$6 / 1M tokens
Cache read
$0.25 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Region
US
Zero data retention
Yes
Data retention
Zero retention
Used for training
No
Data collection
Moderated
No
GDPR compliant
No
HIPAA compliant
No
SOC 2 certified
No
BYOK supported
No

Privacy policy · Terms · Official website · Documentation · Status

Frequently asked questions

What is Qwen: Qwen3.8 2.4T A95B?
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, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.
How much does Qwen: Qwen3.8 2.4T A95B cost?
Input costs start at / 1M tokens and output costs start at $3 / 1M tokens. Provider-level prices vary by service tier.
Are provider discounts available for Qwen: Qwen3.8 2.4T A95B?
Yes. Current provider offers include discounts of up to 50% from list price. The provider table shows list, discounted, and effective prices.
What is the context length of Qwen: Qwen3.8 2.4T A95B?
Qwen: Qwen3.8 2.4T A95B supports a 262,144 token context window and up to 131,100 output tokens.
What capabilities does Qwen: Qwen3.8 2.4T A95B support?
Qwen: Qwen3.8 2.4T A95B supports Streaming, Function calling, Vision, JSON mode.
Which providers offer Qwen: Qwen3.8 2.4T A95B?
Qwen: Qwen3.8 2.4T A95B is available from Alibaba Cloud Int.(SG), DeepInfra, Fireworks.
How do providers handle data privacy for Qwen: Qwen3.8 2.4T A95B?
3 of 3 providers report that customer data is not used for training, and 3 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.

Browse all AI models