AiCostCompare

Claude Sonnet 5 vs Gemini 2.5 Flash (batch)

Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 5 (Anthropic) and Gemini 2.5 Flash (batch) (Google). Green cells mark the better value in each row.

Prices updated Sep 14, 2026, 4:42 PM UTC · refreshed hourly

Claude Sonnet 5

Anthropic

Gemini 2.5 Flash (batch)

Google

Pricing
Input $/1M$2.00$0.15
Output $/1M$10.00$1.25
Blended $/1M (3:1)$4.00$0.425
RAG example (30K in / 2K out)$0.08$0.007
Quality & speed
Intelligence Index38.49.9
Coding Index71.5
Agentic Index44.3
Output speed (tok/s)890
Time to first token124.31s0s
Specs
Context window1M1.05M
Input modalitiestext, image, filefile, image, text, audio, video

FAQ

Which is cheaper, Claude Sonnet 5 or Gemini 2.5 Flash (batch)?

Gemini 2.5 Flash (batch) has the lower blended API price at $0.425 per 1M tokens (3:1 input:output mix), versus $4.00 for the other model. Prices are live from OpenRouter and refresh about hourly.

Which is better for RAG workloads?

For a typical RAG request (30K input / 2K output tokens), Gemini 2.5 Flash (batch) costs about $0.007 per request versus $0.08. Also compare context windows: Claude Sonnet 5 offers 1M and Gemini 2.5 Flash (batch) offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

Claude Sonnet 5 leads on the Artificial Analysis Intelligence Index (38.4 vs 9.9). Check coding and agentic indices on this page for workload-specific tradeoffs.