Price Per TokenPrice Per Token
Qwen
Qwen
vs
Qwen
Qwen

Qwen3 Coder 30B A3B Instruct vs Qwen3.5 397B A17B

A detailed comparison of pricing, benchmarks, and capabilities

114 out of our 483 tracked models have had a price change in March.

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

Qwen3 Coder 30B A3B Instruct wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Better at math

Qwen3.5 397B A17B wins:

  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Supports vision
Price Advantage
Qwen3 Coder 30B A3B Instruct
Benchmark Advantage
Qwen3.5 397B A17B
Context Window
Qwen3.5 397B A17B
Speed
Qwen3.5 397B A17B

Pricing Comparison

Price Comparison

MetricQwen3 Coder 30B A3B InstructQwen3.5 397B A17BWinner
Input (per 1M tokens)$0.07$0.39 Qwen3 Coder 30B A3B Instruct
Output (per 1M tokens)$0.27$0.90 Qwen3 Coder 30B A3B Instruct
Cache Read (per 1M)$0.45$0.45Tie
Using a 3:1 input/output ratio, Qwen3 Coder 30B A3B Instruct is 77% cheaper overall.

Qwen3 Coder 30B A3B Instruct Providers

No provider data available

Qwen3.5 397B A17B Providers

No provider data available

Benchmark Comparison

7
Benchmarks Compared
0
Qwen3 Coder 30B A3B Instruct Wins
3
Qwen3.5 397B A17B Wins

Benchmark Scores

BenchmarkQwen3 Coder 30B A3B InstructQwen3.5 397B A17BWinner
Intelligence Index
Overall intelligence score
20.040.1
Coding Index
Code generation & understanding
19.437.4
Math Index
Mathematical reasoning
29.0--
MMLU Pro
Academic knowledge
70.6--
GPQA
Graduate-level science
51.686.1
LiveCodeBench
Competitive programming
40.3--
AIME
Competition math
29.7--
Qwen3.5 397B A17B significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Qwen3 Coder 30B A3B Instruct
Other models

Context & Performance

Context Window

Qwen3 Coder 30B A3B Instruct
160,000
tokens
Qwen3.5 397B A17B
262,144
tokens
Qwen3.5 397B A17B has a 39% larger context window.

Speed Performance

MetricQwen3 Coder 30B A3B InstructQwen3.5 397B A17BWinner
Tokens/second26.4 tok/s55.5 tok/s
Time to First Token1.49s1.41s
Qwen3.5 397B A17B responds 110% faster on average.

Capabilities

Feature Comparison

FeatureQwen3 Coder 30B A3B InstructQwen3.5 397B A17B
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyQwen3 Coder 30B A3B InstructQwen3.5 397B A17B
LicenseOpen SourceOpen Source
AuthorQwenQwen
ReleasedJul 2025Feb 2026

Qwen3 Coder 30B A3B Instruct Modalities

Input
text
Output
text

Qwen3.5 397B A17B Modalities

Input
textimagevideo
Output
text

Related Comparisons

Compare Qwen3 Coder 30B A3B Instruct with:

Compare Qwen3.5 397B A17B with:

Frequently Asked Questions

Qwen3 Coder 30B A3B Instruct has cheaper input pricing at $0.07/M tokens. Qwen3 Coder 30B A3B Instruct has cheaper output pricing at $0.27/M tokens.
Qwen3.5 397B A17B scores higher on coding benchmarks with a score of 37.4, compared to Qwen3 Coder 30B A3B Instruct's score of 19.4.
Qwen3 Coder 30B A3B Instruct has a 160,000 token context window, while Qwen3.5 397B A17B has a 262,144 token context window.
Qwen3 Coder 30B A3B Instruct does not support vision. Qwen3.5 397B A17B supports vision.