modelgrep
Q

Qwen: Qwen3 Coder 480B A35B

qwen/qwen3-coder

97th smartest of 180ToolsJSON
Use via OpenRouter ↗
Intelligence
24.8
97th of 180
Design Elo
1203
Website
Speed
45
193rd fastest
Latency
654ms
first token
Input price
$0.220
105th cheapest
Context
1.0M
66K max out

How it compares

Smarter than46%
of all ranked models
Faster than37%
of all ranked models
Cheaper than65%
of all ranked models

Overview

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis43th percentile
Intelligence Index
24.8
Coding Index
24.6
Agentic Index
18.3
GPQA Diamond
62%
Humanity's Last Exam
4%
SciCode
36%
Tau²-Bench (agentic)
44%
Design Arena · Elo902 tournaments
Website
1203
codecategories
1195
UI Component
1171
Game Dev
1170
Data Viz
1126

Providers & pricing (7)

ProviderIn $/MOut $/MUptime
Google$0.220$1.80100%
DeepInfrafp4$0.300$1.0098.9%
Venicefp8$0.350$1.50
Novitafp8$0.380$1.55100%
AtlasCloudfp8$0.780$3.80
Alibaba$0.975$4.88
WandBbf16$1.00$1.50

Specifications

Context window1.0M
Max output66K
Knowledge cutoffJun 2025
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Qwen3 Coder 480B A35B FAQ

How much does Qwen3 Coder 480B A35B cost?

Qwen3 Coder 480B A35B costs $0.220 per million input tokens and $1.80 per million output tokens via OpenRouter, making it 105th cheapest of 298 paid models.

How smart is Qwen3 Coder 480B A35B?

Qwen3 Coder 480B A35B scores 24.8 on the Artificial Analysis Intelligence Index, ranking 97th of 180 benchmarked models, with a GPQA Diamond score of 62%.

How fast is Qwen3 Coder 480B A35B?

Qwen3 Coder 480B A35B generates around 45 tokens per second with 654ms time-to-first-token (p50), the 193rd fastest tracked model.

What is Qwen3 Coder 480B A35B's context window?

Qwen3 Coder 480B A35B supports a 1.0M-token context window and can output up to 66K tokens. It accepts text input.

Compare head-to-head