Qwen: Qwen3 Coder Next

qwen/qwen3-coder-next

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering performance comparable to models with 10 to 20x higher active compute, which makes it well suited for cost-sensitive, always-on agent deployment. The model is trained with a strong agentic focus and performs reliably on long-horizon coding tasks, complex tool usage, and recovery from execution failures. With a native 256k context window, it integrates cleanly into real-world CLI and IDE environments and adapts well to common agent scaffolds used by modern coding tools. The model operates exclusively in non-thinking mode and does not emit <think> blocks, simplifying integration for production coding agents.

Model specifications

Input
text
Output
text
Context
262,144 tokens
Max output
262,144 tokens
Input price
$0.18 / 1M tokens
Output price
.35 / 1M tokens
Released
2026-03-01

Capabilities

  • Streaming
  • Function calling
  • JSON mode
  • 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

1 available provider · tier input average $0.18 / 1M tokens · tier output average .35 / 1M tokens

AtlasCloud

Tier: Standard · Region: US

Pricing
Input
$0.18 / 1M tokens
Output
.35 / 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

Privacy policy · Terms · Official website · Documentation · Support

Frequently asked questions

What is Qwen: Qwen3 Coder Next?
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering performance comparable to models with 10 to 20x higher active compute, which makes it well suited for cost-sensitive, always-on agent deployment. The model is trained with a strong agentic focus and performs reliably on long-horizon coding tasks, complex tool usage, and recovery from execution failures. With a native 256k context window, it integrates cleanly into real-world CLI and IDE environments and adapts well to common agent scaffolds used by modern coding tools. The model operates exclusively in non-thinking mode and does not emit <think> blocks, simplifying integration for production coding agents.
How much does Qwen: Qwen3 Coder Next cost?
Input costs start at $0.18 / 1M tokens and output costs start at .35 / 1M tokens. Provider-level prices vary by service tier.
What is the context length of Qwen: Qwen3 Coder Next?
Qwen: Qwen3 Coder Next supports a 262,144 token context window and up to 262,144 output tokens.
What capabilities does Qwen: Qwen3 Coder Next support?
Qwen: Qwen3 Coder Next supports Streaming, Function calling, JSON mode, Playground.
Which providers offer Qwen: Qwen3 Coder Next?
Qwen: Qwen3 Coder Next is available from AtlasCloud.
How do providers handle data privacy for Qwen: Qwen3 Coder Next?
1 of 1 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