Qwen: Qwen3 Coder 480B A35Bqwen
Bottom Line
Qwen: Qwen3 Coder 480B A35B: $0.30/1M input, $1.00/1M output, 262K context. Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...
API Pricing (per 1M tokens)
| Input | $0.30 |
| Output | $1.00 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.47 |
Specs & Performance
| Context Length | 262K |
| Max Output | 66K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text → text |
More from qwen
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Qwen: Qwen3 Coder 480B A35B API cost?
Qwen: Qwen3 Coder 480B A35B costs $0.30/1M input tokens and $1.00/1M output tokens. Blended cost at a 3:1 ratio is about $0.47/1M tokens.
What is the context window of Qwen: Qwen3 Coder 480B A35B?
Qwen: Qwen3 Coder 480B A35B supports a 262K token context window with up to 66K output tokens.
Is Qwen: Qwen3 Coder 480B A35B worth it?
Qwen: Qwen3 Coder 480B A35B has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.