AiCostCompare

Claude Haiku 4.5 vs Gemini 3 Flash Preview (batch)

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and Gemini 3 Flash Preview (batch) (Google). Green cells mark the better value in each row.

Prices updated Nov 18, 2026, 12:01 AM UTC · refreshed nightly

Claude Haiku 4.5

Anthropic

Gemini 3 Flash Preview (batch)

Google

Pricing
Input $/1M$1.00$0.25
Output $/1M$5.00$1.50
Blended $/1M (3:1)$2.00$0.563
RAG example (30K in / 2K out)$0.04$0.0105
Quality & speed
Intelligence Index7.4—
Coding Index43.9—
Agentic Index8—
Output speed (tok/s)——
Time to first token——
Specs
Context window200K1.05M
Input modalitiestext, image, filetext, image, file, audio, video

FAQ

Which is cheaper, Claude Haiku 4.5 or Gemini 3 Flash Preview (batch)?

Gemini 3 Flash Preview (batch) has the lower blended API price at $0.563 per 1M tokens (3:1 input:output mix), versus $2.00 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 Flash Preview (batch) costs about $0.0105 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and Gemini 3 Flash Preview (batch) offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

Claude Haiku 4.5 leads on the Artificial Analysis Intelligence Index (7.4 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.