Skip to main content
Back to Explore

Qwen3 Coder 480B A35B Instruct

Alibaba·Released 2025-07-22
Open Source

Pricing

Input

$0.30

per 1M tokens

Output

$1.80

per 1M tokens

Blended

$0.68

per 1M tokens

Cheaper than 47% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.68

Monthly

$20.25

vs. Similar Models

Magistral Medium 1.2Q:-0.1
$2.75+307%
Qwen3 VL 32B (Reasoning)Q:-0.1
$2.63+289%
Nova 2.0 Lite (high)Q:+0.2
$0.85+26%
Qwen3 235B A22B 2507 InstructQ:+0.2
$0.36-47%

Performance

63

tokens/sec

Faster than 32% of models

1.68

seconds

Faster than 30% of models

1.68

seconds

Faster than 55% of models

Market Median

94 tok/s

33% slower

Median TTFT

1.10s

52% slower

Throughput/Dollar

93

tok/s per $/1M

Speed Comparison

GPT-5.5 (Non-reasoning)
62 tok/s-0%
DeepSeek: R1 Distill Llama 70B
62 tok/s-1%
Qwen3 14B (Reasoning)
62 tok/s-1%

Benchmarks

MMLU-Pro
78.8%
GPQA Diamond
61.8%
HLE
4.4%
LiveCodeBench
58.5%
SciCode
35.9%
TerminalBench Hard
18.9%
MATH-500
94.2%
AIME
47.7%
AIME 2025
39.3%
IFBench
40.5%
Long Context Recall
42.3%
Tau2
43.6%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models