AiCostCompare

Claude Haiku 4.5 vs Gemini 3.5 Flash-Lite

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and Gemini 3.5 Flash-Lite (Google). Green cells mark the better value in each row.

Prices updated Jul 22, 2026, 1:36 AM UTC · refreshed hourly

Claude Haiku 4.5

Anthropic

Gemini 3.5 Flash-Lite

Google

Pricing
Input $/1M$1.00$0.30
Output $/1M$5.00$2.50
Blended $/1M (3:1)$2.00$0.85
RAG example (30K in / 2K out)$0.04$0.014
Quality & speed
Intelligence Index29.636.5
Coding Index43.949.3
Agentic Index16.426.8
Output speed (tok/s)373
Time to first token5.94s
Specs
Context window200K1.05M
Input modalitiestext, image, filetext, image, video, file, audio

FAQ

Which is cheaper, Claude Haiku 4.5 or Gemini 3.5 Flash-Lite?

Gemini 3.5 Flash-Lite has the lower blended API price at $0.85 per 1M tokens (3:1 input:output mix), versus $2.00 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 3.5 Flash-Lite costs about $0.014 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and Gemini 3.5 Flash-Lite offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

Gemini 3.5 Flash-Lite leads on the Artificial Analysis Intelligence Index (36.5 vs 29.6). Check coding and agentic indices on this page for workload-specific tradeoffs.