AiCostCompare

Claude Sonnet 5 vs Gemma 4 26B A4B

Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 5 (Anthropic) and Gemma 4 26B A4B (Google). Green cells mark the better value in each row.

Prices updated Nov 16, 2026, 6:50 PM UTC · refreshed nightly

Claude Sonnet 5

Anthropic

Gemma 4 26B A4B

Google

Pricing
Input $/1M$2.00$0.068
Output $/1M$10.00$0.225
Blended $/1M (3:1)$4.00$0.107
RAG example (30K in / 2K out)$0.08$0.002475
Quality & speed
Intelligence Index——
Coding Index71.539.3
Agentic Index43.62.9
Output speed (tok/s)——
Time to first token——
Specs
Context window1M262K
Input modalitiestext, image, fileimage, text, video

FAQ

Which is cheaper, Claude Sonnet 5 or Gemma 4 26B A4B ?

Gemma 4 26B A4B has the lower blended API price at $0.107 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), Gemma 4 26B A4B costs about $0.002475 per request versus $0.08. Also compare context windows: Claude Sonnet 5 offers 1M and Gemma 4 26B A4B offers 262K.

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.