The Orchestrator › Models › Qwen
Qwen: Qwen3 Coder 480B A35B
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...
Specifications
| Provider | Qwen |
| Model ID | qwen/qwen3-coder |
| Context window | 262K tokens (262,144) |
| Modalities | text → text |
| Tokenizer | Qwen3 |
| Router sources | OpenRouter |
| Released | 2025-07-23 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | qwen/qwen3-coder | $0.3 | $1.00 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.3 | $1.00 | 262K |
Capabilities
Agentic tool useStructured outputs256K+ context window
Supported parameters
frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p