Skip to main content
Back to Explore

Qwen: Qwen3 Coder 480B A35B

Alibaba·Released 2025-07-23
Open Source1.0M ctx

About

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...

Pricing

Input

$0.22

per 1M tokens

Output

$1.80

per 1M tokens

Blended

$0.61

per 1M tokens

Cheaper than 51% of models. Median price is $0.67/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.61

Monthly

$18.45

vs. Similar Models

TheDrummer: Skyfall 36B V2
$0.61-0%
Llama 3.3 Instruct 70B
$0.61-0%
Qwen3 14B (Non-reasoning)
$0.61-0%
WizardLM-2 8x22B
$0.62+1%

Performance

Context Window

1.0M

tokens

Larger than 89% of models

Max Output

66K

tokens

6% of context

Context Window Comparison

Z.ai: GLM 5.2
1.0MSame
Google: Gemini 3.5 Flash
1.0MSame
Google: Gemini 3.1 Pro Preview
1.0MSame

Open Source

Quick Compare

Similar Models

Compare all 7 models