AiCostCompare

Claude Sonnet 5 vs GPT-3.5 Turbo 16k

Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 5 (Anthropic) and GPT-3.5 Turbo 16k (OpenAI). Green cells mark the better value in each row.

Prices updated Nov 18, 2026, 11:26 AM UTC · refreshed nightly

Claude Sonnet 5

Anthropic

GPT-3.5 Turbo 16k

OpenAI

Pricing
Input $/1M$2.00$3.00
Output $/1M$10.00$4.00
Blended $/1M (3:1)$4.00$3.25
RAG example (30K in / 2K out)$0.08$0.098
Quality & speed
Intelligence Index——
Coding Index71.5—
Agentic Index43.6—
Output speed (tok/s)——
Time to first token——
Specs
Context window1M16K
Input modalitiestext, image, filetext

FAQ

Which is cheaper, Claude Sonnet 5 or GPT-3.5 Turbo 16k?

GPT-3.5 Turbo 16k has the lower blended API price at $3.25 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), Claude Sonnet 5 costs about $0.08 per request versus $0.098. Also compare context windows: Claude Sonnet 5 offers 1M and GPT-3.5 Turbo 16k offers 16K.

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.