ModelBench
Alibaba Qwen logo
Models/Alibaba Qwen

Qwen3-Coder 480B-A35B Instruct

Open Qwen coding heavyweight for repository reasoning and agentic engineering

Source-linked qwen Open weights Released 2025-04
API data Report
Input modalitiesT
Output modalitiesT
Input price$1.5/1M tokens
Output price$7.5/1M tokens
Context window262.144K
Max output65.536K
Overview

Capabilities and specifications

× Reasoning No
✓ Tool calling Yes
? Structured output Unknown
× Attachments No
× Vision input No
✓ Open weights Yes
Model family
qwen
Knowledge cutoff
2025-04
License
Not documented
Release date
2025-04
Model ID
alibaba/qwen3-coder-480b-a35b-instruct
Inference availability

Provider pricing and availability

Provider-specific identifiers, limits, and prices per million tokens.

Report a price
Providers offering Qwen3-Coder 480B-A35B Instruct
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
Merge Gateway qwen/qwen3-coder-480b-a35b-instruct 131.072K $0.22 $1.8 - Not listed Docs
Abacus Qwen/Qwen3-Coder-480B-A35B-Instruct 262.144K $0.29 $1.2 - Tools Docs
LLM Gateway qwen3-coder-480b-a35b-instruct 262.144K $0.3 $1.3 - Tools Docs
Charm Hyper qwen3-coder-480b-a35b-instruct-int4-mixed-ar 106K $0.569 $2.135 - Tools Docs
Alibaba (China) qwen3-coder-480b-a35b-instruct 262.144K $0.861 $3.441 - Tools Docs
Alibaba qwen3-coder-480b-a35b-instruct 262.144K $1.5 $7.5 - Tools Docs

Capability badges appear only when the provider catalog explicitly lists support.

Serving quality

Performance and reliability

Observed serving measurements stay separate from model specifications and are never estimated from price or model size.

Throughput Not reported

Generation speed; higher is faster.

Latency / TTFT Not reported

Time until the first output token arrives.

Uptime Not reported

Successful requests over a measured period.

Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.

Published evaluations

Benchmarks

Raw results remain attached to their original source and version.

Benchmark registry
SWE-Bench Pro - Unversioned - resolve rateTop 8 reported models
Claude Fable 5
80.3
Claude Opus 4.8
69.2
Grok 4.5
64.7
GPT-5.6 Sol
64.6
Claude Opus 4.7
64.3
GPT-5.6 Terra
63.4
Claude Sonnet 5
63.2
Qwen3-Coder 480B-A35B Instruct
38.7
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
No recent changes detected

This record has not changed in the retained import history.

Public API

Use this record

Fetch the complete source-linked model record without an API key.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/alibaba/qwen3-coder-480b-a35b-instruct
curl
curl "https://www.modelbench.lol/api/v1/models/alibaba/qwen3-coder-480b-a35b-instruct"