Qwen: Qwen2.5 7B Instruct

qwen/qwen2.5-7b-instruct

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots. Long-context Support up to 128K tokens and can generate up to 8K tokens. Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. This repo contains the instruction-tuned 7B Qwen2.5 model, which has the following features: Type: Causal Language Models Training Stage: Pretraining & Post-training Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias Number of Parameters: 7.61B Number of Paramaters (Non-Embedding): 6.53B Number of Layers: 28 Number of Attention Heads (GQA): 28 for Q and 4 for KV Context Length: Full 131,072 tokens and generation 8192 tokens Please refer to this section for detailed instructions on how to deploy Qwen2.5 for handling long texts.

Model specifications

Context
131,072 tokens
Max output
8,192 tokens
Input price
$0.04 / 1M tokens
Output price
$0.1 / 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 · tier input average $0.1075 / 1M tokens · tier output average $0.4 / 1M tokens

AtlasCloud

Tier: Standard · Region: US

Pricing
Input
$0.04 / 1M tokens
Output
$0.1 / 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

Alibaba Cloud Int.(SG)

Tier: Standard · Region: SG · Quantization: int8

Pricing
Input
$0.175 / 1M tokens
Output
$0.7 / 1M tokens

No provider discount is currently published.

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

Frequently asked questions

What is Qwen: Qwen2.5 7B Instruct?
Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots. Long-context Support up to 128K tokens and can generate up to 8K tokens. Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. This repo contains the instruction-tuned 7B Qwen2.5 model, which has the following features: Type: Causal Language Models Training Stage: Pretraining & Post-training Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias Number of Parameters: 7.61B Number of Paramaters (Non-Embedding): 6.53B Number of Layers: 28 Number of Attention Heads (GQA): 28 for Q and 4 for KV Context Length: Full 131,072 tokens and generation 8192 tokens Please refer to this section for detailed instructions on how to deploy Qwen2.5 for handling long texts.
How much does Qwen: Qwen2.5 7B Instruct cost?
Input costs start at $0.04 / 1M tokens and output costs start at $0.1 / 1M tokens. Provider-level prices vary by service tier.
What is the context length of Qwen: Qwen2.5 7B Instruct?
Qwen: Qwen2.5 7B Instruct supports a 131,072 token context window and up to 8,192 output tokens.
What capabilities does Qwen: Qwen2.5 7B Instruct support?
Qwen: Qwen2.5 7B Instruct supports Streaming, Playground.
Which providers offer Qwen: Qwen2.5 7B Instruct?
Qwen: Qwen2.5 7B Instruct is available from AtlasCloud, Alibaba Cloud Int.(SG).
How do providers handle data privacy for Qwen: Qwen2.5 7B Instruct?
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