Qwen / Qwen3 Coder 480B (A35B) Instruct
Released: 7/22/2025Qwen3 Coder 480B (A35B) Instruct is an LLM designed for complex coding, agentic automation, tool use, and repository-scale code understanding.
It excels in handling tasks that require advanced code generation, extended context management (supporting up to 256K tokens natively), and agentic interactions for coding assistants, comparable to models such as Claude Sonnet. Its Mixture-of-Experts architecture allows it to efficiently address diverse and challenging programming problems at scale.
Some other noteworthy features of Qwen3 Coder 480B (A35B) Instruct include its support for agentic browser-based workflows and seamless integration with developer tools for large-scale code analysis and function-calling automation.
Metric | Value |
---|---|
Parameter Count | 480 billion (35 billion active) |
Mixture of Experts | Yes |
Active Parameter Count | 35 billion |
Context Length | 262,144 tokens |
Multilingual | Yes |
Quantized* | No |
*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.
Qwen models available on Oxen.ai
Modality | Price (1M tokens) | ||||
---|---|---|---|---|---|
Model | Inference provider | Input | Output | Input | Output |
![]() | text | text | $0.90 | $0.90 | |
![]() | text | text | $0.22 | $0.88 | |
![]() | text | text | $0.90 | $0.90 | |
![]() | text | text | $2.00 | $2.00 | |
![]() | text | text | N/A | N/A | |
![]() | text | text | $0.90 | $0.90 | |
![]() | text | text | $0.45 | $1.80 | |
![]() | text | text | $0.90 | $0.90 |