Price Per TokenPrice Per Token
Anthropic
Anthropic
vs
OpenAI
OpenAI

Claude Sonnet 4 vs GPT-OSS-20b

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

Claude Sonnet 4 wins:

  • Larger context window
  • Higher intelligence benchmark
  • Better at coding
  • Supports vision
  • Has reasoning mode
  • Supports tool calls

GPT-OSS-20b wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Faster response time
  • Better at math
Price Advantage
GPT-OSS-20b
Benchmark Advantage
Claude Sonnet 4
Context Window
Claude Sonnet 4
Speed
GPT-OSS-20b

Pricing Comparison

Price Comparison

MetricClaude Sonnet 4GPT-OSS-20bWinner
Input (per 1M tokens)$3.00$0.02 GPT-OSS-20b
Output (per 1M tokens)$15.00$0.10 GPT-OSS-20b
Cache Read (per 1M)$300000.00N/A Claude Sonnet 4
Cache Write (per 1M)$3750000.00N/A Claude Sonnet 4
Using a 3:1 input/output ratio, GPT-OSS-20b is 99% cheaper overall.

Claude Sonnet 4 Providers

Amazon Bedrock $3.00 (Cheapest)
OpenRouter $3.00 (Cheapest)
Google $3.00 (Cheapest)
Anthropic $3.00 (Cheapest)

GPT-OSS-20b Providers

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

Benchmark Comparison

8
Benchmarks Compared
3
Claude Sonnet 4 Wins
3
GPT-OSS-20b Wins

Benchmark Scores

BenchmarkClaude Sonnet 4GPT-OSS-20bWinner
Intelligence Index
Overall intelligence score
32.724.7
Coding Index
Code generation & understanding
29.418.1
Math Index
Mathematical reasoning
38.089.3
MMLU Pro
Academic knowledge
83.774.8
GPQA
Graduate-level science
68.368.8
LiveCodeBench
Competitive programming
44.977.7
Aider
Real-world code editing
61.3--
AIME
Competition math
40.7--
Claude Sonnet 4 significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Claude Sonnet 4
Other models

Context & Performance

Context Window

Claude Sonnet 4
1,000,000
tokens
Max output: 64,000 tokens
GPT-OSS-20b
131,072
tokens
Max output: 131,072 tokens
Claude Sonnet 4 has a 87% larger context window.

Speed Performance

MetricClaude Sonnet 4GPT-OSS-20bWinner
Tokens/second66.3 tok/s309.0 tok/s
Time to First Token1.90s0.51s
GPT-OSS-20b responds 366% faster on average.

Capabilities

Feature Comparison

FeatureClaude Sonnet 4GPT-OSS-20b
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyClaude Sonnet 4GPT-OSS-20b
LicenseProprietaryOpen Source
AuthorAnthropicOpenAI
ReleasedMay 2025Aug 2025

Claude Sonnet 4 Modalities

Input
imagetextfile
Output
text

GPT-OSS-20b Modalities

Input
text
Output
text

Related Comparisons

Compare Claude Sonnet 4 with:

Compare GPT-OSS-20b 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.
Claude Sonnet 4 scores higher on coding benchmarks with a score of 29.4, compared to GPT-OSS-20b's score of 18.1.
Claude Sonnet 4 has a 1,000,000 token context window, while GPT-OSS-20b has a 131,072 token context window.
Claude Sonnet 4 supports vision. GPT-OSS-20b does not support vision.