Qwen: Qwen3 235B A22B Instruct 2507

qwen/qwen3-235b-a22b-instruct-2507

Qwen3-235B-A22B-Instruct-2507 has the following features: Type: Causal Language Models Training Stage: Pretraining & Post-training Number of Parameters: 235B in total and 22B activated Number of Paramaters (Non-Embedding): 234B Number of Layers: 94 Number of Attention Heads (GQA): 64 for Q and 4 for KV Number of Experts: 128 Number of Activated Experts: 8 Context Length: 262,144 natively and extendable up to 1,010,000 tokens NOTE: This model supports only non-thinking mode and does not generate <think></think> blocks in its output. Meanwhile, specifying enable_thinking=False is no longer required.

Model specifications

Context
131,072 tokens
Max output
8,192 tokens
Input price
$0.2 / 1M tokens
Output price
$0.88 / 1M tokens
Released
2026-02-05

Capabilities

  • Streaming
  • Playground

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

2 available providers · discounts up to 50% · tier input average $0.1575 / 1M tokens · tier output average $0.67 / 1M tokens

Alibaba Cloud Int.(SG)

Tier: Standard · Region: SG · Quantization: int8

Pricing
Input
$0.115 / 1M tokens
Output
$0.46 / 1M tokens
Discounts
  • Input: 50% off — list $0.23 / 1M tokens, discounted $0.115 / 1M tokens, effective $0.115 / 1M tokens
  • Output: 50% off — list $0.92 / 1M tokens, discounted $0.46 / 1M tokens, effective $0.46 / 1M tokens
Data privacy and compliance
Region
SG
Zero data retention
No
Data retention
30-day retention
Used for training
No
Data collection
Moderated
Yes
GDPR compliant
Yes
HIPAA compliant
No
SOC 2 certified
Yes
BYOK supported
Yes

AtlasCloud

Tier: Standard · Region: US

Pricing
Input
$0.2 / 1M tokens
Output
$0.88 / 1M tokens

No provider discount is currently published.

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

Frequently asked questions

What is Qwen: Qwen3 235B A22B Instruct 2507?
Qwen3-235B-A22B-Instruct-2507 has the following features: Type: Causal Language Models Training Stage: Pretraining & Post-training Number of Parameters: 235B in total and 22B activated Number of Paramaters (Non-Embedding): 234B Number of Layers: 94 Number of Attention Heads (GQA): 64 for Q and 4 for KV Number of Experts: 128 Number of Activated Experts: 8 Context Length: 262,144 natively and extendable up to 1,010,000 tokens NOTE: This model supports only non-thinking mode and does not generate <think></think> blocks in its output. Meanwhile, specifying enable_thinking=False is no longer required.
How much does Qwen: Qwen3 235B A22B Instruct 2507 cost?
Input costs start at $0.2 / 1M tokens and output costs start at $0.88 / 1M tokens. Provider-level prices vary by service tier.
Are provider discounts available for Qwen: Qwen3 235B A22B Instruct 2507?
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 235B A22B Instruct 2507?
Qwen: Qwen3 235B A22B Instruct 2507 supports a 131,072 token context window and up to 8,192 output tokens.
What capabilities does Qwen: Qwen3 235B A22B Instruct 2507 support?
Qwen: Qwen3 235B A22B Instruct 2507 supports Streaming, Playground.
Which providers offer Qwen: Qwen3 235B A22B Instruct 2507?
Qwen: Qwen3 235B A22B Instruct 2507 is available from Alibaba Cloud Int.(SG), AtlasCloud.
How do providers handle data privacy for Qwen: Qwen3 235B A22B Instruct 2507?
2 of 2 providers report that customer data is not used for training, and 0 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.

Browse all AI models