All Models
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...
Benchmarks
Available Providers (19)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Alibaba Coding Plan (China) | qwen3-coder-next | $0/MTok | $0/MTok | 262.1K | 65.5K | |
 Alibaba Coding Plan | qwen3-coder-next | $0/MTok | $0/MTok | 262.1K | 65.5K | |
 LLM Gateway | embercloud/qwen3-coder-next | $0.11/MTok | $0.68/MTok | 262.1K | 262.1K | |
 DevPass (LLM Gateway) | qwen3-coder-next | $0.11/MTok | $0.68/MTok | 262.1K | 65.5K | |
 OpenRouter | qwen/qwen3-coder-next | $0.12/MTok | $0.80/MTok | 262.1K | 235.9K | |
 Merge Gateway | qwen/qwen3-coder-next | $0.15/MTok | $0.80/MTok | 262.1K | 65.5K | |
 Cortecs | qwen3-coder-next | $0.17/MTok | $0.89/MTok | 256K | 256K | |
 NanoGPT | qwen/qwen3-coder-next | $0.20/MTok | $1.50/MTok | 262.1K | 65.5K | |
 NovitaAI | qwen/qwen3-coder-next | $0.20/MTok | $1.50/MTok | 262.1K | 65.5K | |
 Hugging Face | Qwen/Qwen3-Coder-Next | $0.20/MTok | $1.50/MTok | 262.1K | 65.5K | |
 Jiekou.AI | qwen/qwen3-coder-next | $0.20/MTok | $1.50/MTok | 262.1K | 65.5K | |
 Ofox | qwen/qwen3-coder-next | $0.20/MTok | $1.50/MTok | 256K | 64K | |
| Ofox | bailian/qwen3-coder-next | $0.20/MTok | $1.50/MTok | 262.1K | 65.5K | |
 Regolo AI | qwen3-coder-next | $0.30/MTok | $1.20/MTok | 262.1K | 16.4K | |
 Kilo Gateway | qwen/qwen3-coder-next | $0.30/MTok | $1.50/MTok | 262.1K | 235.9K | |
 Eden AI | qwen/qwen3-coder-next | $0.30/MTok | $1.50/MTok | 262.1K | 65.5K | |
| Eden AI | qwen/qwen3-coder-next@eu | $0.30/MTok | $1.50/MTok | 262.1K | 65.5K | |
 Vercel AI Gateway | alibaba/qwen3-coder-next | $0.50/MTok | $1.20/MTok | 256K | 256K | |
 Amazon Bedrock | qwen.qwen3-coder-next | $0.50/MTok | $1.20/MTok | 262.1K | 65.5K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output