AiCostCompare

Claude Sonnet 5 vs gpt-oss-safeguard-20b

Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 5 (Anthropic) and gpt-oss-safeguard-20b (OpenAI). Green cells mark the better value in each row.

Prices updated Nov 16, 2026, 9:02 PM UTC · refreshed nightly

Claude Sonnet 5

Anthropic

gpt-oss-safeguard-20b

OpenAI

Pricing
Input $/1M$2.00$0.075
Output $/1M$10.00$0.30
Blended $/1M (3:1)$4.00$0.131
RAG example (30K in / 2K out)$0.08$0.00285
Quality & speed
Intelligence Index——
Coding Index71.5—
Agentic Index43.6—
Output speed (tok/s)——
Time to first token——
Specs
Context window1M131K
Input modalitiestext, image, filetext

FAQ

Which is cheaper, Claude Sonnet 5 or gpt-oss-safeguard-20b?

gpt-oss-safeguard-20b has the lower blended API price at $0.131 per 1M tokens (3:1 input:output mix), versus $4.00 for the other model. Prices are live from OpenRouter and refresh nightly.

Which is better for RAG workloads?

For a typical RAG request (30K input / 2K output tokens), gpt-oss-safeguard-20b costs about $0.00285 per request versus $0.08. Also compare context windows: Claude Sonnet 5 offers 1M and gpt-oss-safeguard-20b offers 131K.

Which scores higher on Artificial Analysis benchmarks?

Intelligence Index scores are unavailable or tied for these two models. Compare coding index, speed, and price on this page to decide.