AiCostCompare

Claude Sonnet 5 vs Gemini 3.8 Flash

Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 5 (Anthropic) and Gemini 3.8 Flash (Google). Green cells mark the better value in each row.

Prices updated Nov 16, 2026, 2:25 PM UTC · refreshed nightly

Claude Sonnet 5

Anthropic

Gemini 3.8 Flash

Google

Pricing
Input $/1M$2.00$0.825
Output $/1M$10.00$4.13
Blended $/1M (3:1)$4.00$1.65
RAG example (30K in / 2K out)$0.08$0.033
Quality & speed
Intelligence Index—30.8
Coding Index71.576.3
Agentic Index43.640.2
Output speed (tok/s)——
Time to first token——
Specs
Context window1M1.05M
Input modalitiestext, image, filetext, image, video, file, audio

FAQ

Which is cheaper, Claude Sonnet 5 or Gemini 3.8 Flash?

Gemini 3.8 Flash has the lower blended API price at $1.65 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), Gemini 3.8 Flash costs about $0.033 per request versus $0.08. Also compare context windows: Claude Sonnet 5 offers 1M and Gemini 3.8 Flash offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

Gemini 3.8 Flash leads on the Artificial Analysis Intelligence Index (30.8 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.