# Qwen3-Coder

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 repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts).

Pricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.

## Model Information

- **Organization**: [qwen](/llm.txt)
- **Slug**: qwen3-coder
- **Available at Providers**: 31
- **Release Date**: January 1, 2025

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [FastRouter](/llm/fastrouter.txt) | Qwen: Qwen3 Coder  | 0.40 | 1.60 |  | [View](https://fastrouter.ai/models/qwen/qwen3-coder) |
| [Helicone](/llm/helicone.txt) | Qwen3 Coder 480B A35B Instruct Turbo | 0.22 | 0.95 |  | [View](https://www.helicone.ai/model/qwen3-coder) |
| [Mammouth AI](/llm/mammouth.txt) | qwen3-coder | 0.50 | 2.00 |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | Qwen 3 Coder 480B |  |  |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | Qwen3 Coder 480B TEE |  |  |  |  |
| [Ollama Cloud](/llm/ollama.txt) | qwen3-coder |  |  |  | [View](https://ollama.com/library/qwen3-coder:480b) |
| [OpenRouter](/llm/openrouter.txt) | Qwen3 Coder 480B A35B | 0.22 | 1.00 |  | [View](https://openrouter.ai/qwen/qwen3-coder-480b-a35b-07-25) |
| [ValorGPT](/llm/valorgpt.txt) | Qwen3 Coder 480B A35B |  |  |  | [View](https://www.valorgpt.com/models/qwen-qwen3-coder) |
| [ValorGPT](/llm/valorgpt.txt) | Qwen3 Coder 480B A35B |  |  | Yes | [View](https://www.valorgpt.com/models/qwen-qwen3-coder-free) |
| [ValorGPT](/llm/valorgpt.txt) | Qwen3 Coder 480B A35B (exacto) |  |  |  | [View](https://www.valorgpt.com/models/qwen-qwen3-coder-exacto) |
| [Vercel AI Gateway](/llm/vercel.txt) | Qwen3 Coder 480B A35B Instruct | 0.40 | 1.60 |  |  |
| [Yupp](/llm/yupp.txt) | Qwen 3 Coder (OpenRouter) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | Qwen3 Coder 480B A35B (exacto) (OpenRouter) |  |  |  |  |
| [ZenMUX](/llm/zenmux.txt) | Qwen: Qwen3-Coder | 1.25 | 5.01 |  |  |
| [Atlas Cloud](/llm/atlascloud.txt) | Qwen3 Coder | 0.69 | 2.70 |  | [View](https://www.atlascloud.ai/models/Qwen/Qwen3-Coder) |
| [LangDB](/llm/langdb.txt) | qwen3-coder |  |  |  | [View](https://langdb.ai/app/models) |
| [Kilo Code](/llm/kilocode.txt) | Qwen: Qwen3 Coder 480B A35B | 0.22 | 1.00 |  | [View](https://kilo.ai/models/qwen/qwen3-coder) |
| [Kilo Code](/llm/kilocode.txt) | Qwen: Qwen3 Coder 480B A35B (exacto) | 0.22 | 1.80 |  | [View](https://kilo.ai/models/qwen/qwen3-coder) |
| [Google Vertex AI](/llm/googlevertex.txt) | Qwen3 Coder |  |  |  |  |
| [302.AI](/llm/302ai.txt) | sophnet/Qwen3-Coder | 0.86 | 3.43 |  | [View](https://302ai-en.apifox.cn/api-319727732) |
| [Okara](/llm/okara.txt) | Qwen 3 Coder |  |  |  | [View](https://okara.ai/ai-models/qwen3-coder) |
| [Chats-LLM](/llm/chatsllm.txt) | Qwen: Qwen3 Coder 480B A35B | 0.22 | 1.00 |  |  |
| [CometAPI](/llm/cometapi.txt) |  | 0.24 | 0.96 |  |  |
| [ApiYI](/llm/apiyi.txt) | qwen3-coder |  |  |  |  |
| [WaveSpeed AI](/llm/wavespeed.txt) | qwen3-coder | 0.24 | 1.10 |  |  |
| [OpenRouter](/llm/openrouter.txt) | Qwen3 Coder 480B A35B (free) | 0.00 | 0.00 | Yes | [View](https://openrouter.ai/qwen/qwen3-coder-480b-a35b-07-25:free) |
| [OpenRouter](/llm/openrouter.txt) | Qwen3 Coder 480B A35B (exacto) | 0.22 | 1.80 |  | [View](https://openrouter.ai/qwen/qwen3-coder-480b-a35b-07-25:exacto) |
| [Writingmate](/llm/writingmate.txt) | Qwen: Qwen3 Coder 480B A35B (exacto) |  |  |  | [View](https://writingmate.ai/models/qwen/qwen3-coder) |
| [Blackbox AI](/llm/blackboxai.txt) | blackboxai/qwen/qwen3-coder:free |  |  |  |  |
| [Kilo Code](/llm/kilocode.txt) | Qwen: Qwen3 Coder 480B A35B (free) | 0.00 | 0.00 | Yes |  |
| [LLM Stats](/llm/llmstats.txt) | Qwen3-Coder |  |  |  |  |

---

[← Back to all providers](/llm.txt)