Price Per TokenPrice Per Token
OpenAI
OpenAI
vs
Qwen
Qwen

GPT-OSS-20b vs Qwen3 Coder 480B A35B (exacto)

A detailed comparison of pricing, benchmarks, and capabilities

Sponsor Price Per Token Reach 5000+ developers comparing LLM APIs

116 out of our 296 tracked models have had a price change in January.

Make informed model choices with updates on pricing, new releases, and tools with our weekly newsletter.

Key Takeaways

GPT-OSS-20b wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Better at math

Qwen3 Coder 480B A35B (exacto) wins:

  • Larger context window
  • Supports tool calls
Price Advantage
GPT-OSS-20b
Benchmark Advantage
GPT-OSS-20b
Context Window
Qwen3 Coder 480B A35B (exacto)
Speed
GPT-OSS-20b

Pricing Comparison

Price Comparison

MetricGPT-OSS-20bQwen3 Coder 480B A35B (exacto)Winner
Input (per 1M tokens)$0.02$0.22 GPT-OSS-20b
Output (per 1M tokens)$0.10$0.95 GPT-OSS-20b
Using a 3:1 input/output ratio, GPT-OSS-20b is 90% cheaper overall.

GPT-OSS-20b Providers

GMICloud $0.02 (Cheapest)
DeepInfra $0.03
Parasail $0.04
Phala $0.04
SiliconFlow $0.04

Qwen3 Coder 480B A35B (exacto) Providers

Chutes $0.22 (Cheapest)
OpenRouter $0.22 (Cheapest)
Google $0.22 (Cheapest)
SiliconFlow $0.25
DeepInfra $0.28

Benchmark Comparison

6
Benchmarks Compared
0
GPT-OSS-20b Wins
0
Qwen3 Coder 480B A35B (exacto) Wins

Benchmark Scores

BenchmarkGPT-OSS-20bQwen3 Coder 480B A35B (exacto)Winner
Intelligence Index
Overall intelligence score
24.7--
Coding Index
Code generation & understanding
18.1--
Math Index
Mathematical reasoning
89.3--
MMLU Pro
Academic knowledge
74.8--
GPQA
Graduate-level science
68.8--
LiveCodeBench
Competitive programming
77.7--
GPT-OSS-20b significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
GPT-OSS-20b
Other models

Context & Performance

Context Window

GPT-OSS-20b
131,072
tokens
Max output: 131,072 tokens
Qwen3 Coder 480B A35B (exacto)
262,144
tokens
Max output: 262,144 tokens
Qwen3 Coder 480B A35B (exacto) has a 50% larger context window.

Speed Performance

MetricGPT-OSS-20bQwen3 Coder 480B A35B (exacto)Winner
Tokens/second309.0 tok/sN/A
Time to First Token0.51sN/A

Capabilities

Feature Comparison

FeatureGPT-OSS-20bQwen3 Coder 480B A35B (exacto)
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyGPT-OSS-20bQwen3 Coder 480B A35B (exacto)
LicenseOpen SourceOpen Source
AuthorOpenAIQwen
ReleasedAug 2025Jul 2025

GPT-OSS-20b Modalities

Input
text
Output
text

Qwen3 Coder 480B A35B (exacto) Modalities

Input
text
Output
text

Related Comparisons

Compare GPT-OSS-20b with:

Compare Qwen3 Coder 480B A35B (exacto) with:

Frequently Asked Questions

GPT-OSS-20b has cheaper input pricing at $0.02/M tokens. GPT-OSS-20b has cheaper output pricing at $0.10/M tokens.
GPT-OSS-20b scores higher on coding benchmarks with a score of 18.1, compared to Qwen3 Coder 480B A35B (exacto)'s score of N/A.
GPT-OSS-20b has a 131,072 token context window, while Qwen3 Coder 480B A35B (exacto) has a 262,144 token context window.
GPT-OSS-20b does not support vision. Qwen3 Coder 480B A35B (exacto) does not support vision.