Qwen3-Coder 480B-A35B Instruct
Summary
Qwen3-Coder 480B-A35B Instruct is an open-weight language model from Alibaba (Qwen), released on Apr 2025. It accepts text and generates text, with a 262K-token context window and up to 66K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.25 per million input tokens and $1 per million output tokens (SiliconFlow), across 4 providers we track. Alibaba (Qwen) has deprecated this model.
Open Qwen coding heavyweight for repository reasoning and agentic engineering
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Alibaba (Qwen) |
|---|---|
| Release date | Apr 2025 [models.dev] |
| Status | Deprecated [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 480B [Hugging Face] |
| Context window | 262K (262,144 tokens) [models.dev] |
| Max output | 66K tokens [models.dev] |
| Knowledge cutoff | Apr 2025 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | Yes [models.dev] |
| Hugging Face | Qwen/Qwen3-Coder-480B-A35B-Instruct [Hugging Face] |
Qwen3-Coder 480B-A35B Instruct API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| SiliconFlow Qwen/Qwen3-Coder-480B-A35B-Instruct | $0.25 | $1 | – | 262K | models.dev, 18 Nov 2026 |
| DeepInfra Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | $0.30 | $1 | $0.10 | 262K | models.dev, 18 Nov 2026 |
| OpenRouter qwen/qwen3-coder | $0.30 | $1 | $0.10 | 262K | OpenRouter, 18 Nov 2026 |
| Hugging Face Inference Providers Qwen/Qwen3-Coder-480B-A35B-Instruct | $2 | $2 | – | 262K | models.dev, 18 Nov 2026 |
Running Qwen3-Coder 480B-A35B Instruct locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 291 GB | 294 GB | 300 GB |
| Q8_0 (8-bit) | 510 GB | 513 GB | 519 GB |
| FP16 / BF16 (16-bit) | 960 GB | 963 GB | 969 GB |
At 4-bit with an 8K conversation, Qwen3-Coder 480B-A35B Instruct needs about 294 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.
Frequently asked questions
What is the context window of Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct has a context window of 262,144 tokens (262K) and can generate up to 65,536 tokens in a single response, according to models.dev.
How much does the Qwen3-Coder 480B-A35B Instruct API cost?
Qwen3-Coder 480B-A35B Instruct is listed from $0.25 per million input tokens and $1 per million output tokens (SiliconFlow). Prices last verified 18 Nov 2026.
Is Qwen3-Coder 480B-A35B Instruct open source?
Qwen3-Coder 480B-A35B Instruct is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3-Coder-480B-A35B-Instruct under the apache-2.0 license. Check the license terms before commercial use.
When was Qwen3-Coder 480B-A35B Instruct released?
Alibaba (Qwen) released Qwen3-Coder 480B-A35B Instruct on Apr 2025, according to models.dev.
Which providers offer Qwen3-Coder 480B-A35B Instruct?
We track Qwen3-Coder 480B-A35B Instruct on 4 providers: SiliconFlow, DeepInfra, OpenRouter, Hugging Face Inference Providers.
How much VRAM does Qwen3-Coder 480B-A35B Instruct need?
About 294 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 513 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| DeepSeek V3 0324 | DeepSeek | 24 Mar 2025 | 164K | $0.25 | $1 | Open |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | Meta | 5 Apr 2025 | 128K | $0.24 | $0.85 | Open |
| Mistral Large 3 | Mistral AI | 1 Nov 2024 | 262K | $0.50 | $1.50 | Open |
| DeepSeek V3.1 | DeepSeek | 21 Aug 2025 | 164K | $0.25 | $0.95 | Open |
| Uncensored | Cognitivecomputations | 9 Jul 2025 | 128K | $0.20 | $0.90 | Open |
| Mistral Small 3.2 24B | Mistral AI | 20 Jun 2025 | 256K | $0.10 | $0.30 | Open |
Change history
- No longer listed on vercel
- Now listed on DeepInfra
- License changed from none to apache-2.0
- Parameter count changed from none to 480B
- Now listed on OpenRouter
- No longer listed on alibaba
- No longer listed on amazon-bedrock
- Now listed on vercel
- Status changed from active to deprecated
- No longer listed on novita-ai
Sources
- https://openrouter.ai/qwen/qwen3-coder
- https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3-coder-480b-a35b-instruct.toml
- https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/Qwen/Qwen3-Coder-480B-A35B-Instruct.toml
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-Coder-480B-A35B-Instruct.toml