Primary use stated or inferred cautiously from official documentation.
Qwen3‑Coder 480B A35B
Open MoE model specialized in software engineering, repository navigation, and extended tool use.
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
Limits and integration
| API ID | Qwen3-Coder-480B-A35B-Instruct |
|---|---|
| Model type | Code · Text and reasoning |
| Access model | API and open weights |
| License | Apache 2.0 |
| Deployment | API, local, or private cloud |
| Release | 22 JUL 2025 |
| Knowledge cutoff | Not published |
| Entrance | Text · Code |
| Exit | Text · Code |
| Context window | 256,000 native tokens · up to 1M extended |
| maximum output | Not published |
| Reasoning | Optimized for agents |
| Published tools | Features · Qwen Code |
| Structured Outings | Not applicable or not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Downloadable weights |
| Verified platforms | Alibaba Cloud · Hugging Face · Qwen Code |
Code agents, large repositories, and multi-stage engineering tasks.
Compare the harness, tools, token budget, and context used in each benchmark.
What it can do
Orientation
Code agents, large repositories, and multi-stage engineering tasks.
Context
256,000 native tokens · up to 1M extended · Not published
Tools and integration
Functions · Qwen Code
Access
Alibaba Cloud and weights
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | Not published | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | Not published | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Consult the primary source: the billing unit depends on the model type and access channel.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
How to read the results
A public benchmark provides guidance, but does not replace an evaluation with your data, tools, budget, and error tolerance.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| SWE-bench Verified | Published open SOTA result | Software problems solved | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
Chronology
Qwen3‑Coder 480B A35B
Version added to Inferama's verified catalog.