AiCostCompare

Claude Haiku 4.5 vs Gemini 4 Hydrogen (batch)

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and Gemini 4 Hydrogen (batch) (Google). Green cells mark the better value in each row.

Prices updated Nov 17, 2026, 12:15 PM UTC · refreshed nightly

Claude Haiku 4.5

Anthropic

Gemini 4 Hydrogen (batch)

Google

Pricing
Input $/1M$1.00$0.75
Output $/1M$5.00$3.75
Blended $/1M (3:1)$2.00$1.50
RAG example (30K in / 2K out)$0.04$0.03
Quality & speed
Intelligence Index7.453.9
Coding Index43.9—
Agentic Index8—
Output speed (tok/s)——
Time to first token——
Specs
Context window200K1.05M
Input modalitiestext, image, fileaudio, file, image, text, video

FAQ

Which is cheaper, Claude Haiku 4.5 or Gemini 4 Hydrogen (batch)?

Gemini 4 Hydrogen (batch) has the lower blended API price at $1.50 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 4 Hydrogen (batch) costs about $0.03 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and Gemini 4 Hydrogen (batch) offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

Gemini 4 Hydrogen (batch) leads on the Artificial Analysis Intelligence Index (53.9 vs 7.4). Check coding and agentic indices on this page for workload-specific tradeoffs.