AiCostCompare

Claude Haiku 4.5 vs Gemma 3 27B

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and Gemma 3 27B (Google). Green cells mark the better value in each row.

Prices updated Nov 16, 2026, 8:45 PM UTC · refreshed nightly

Claude Haiku 4.5

Anthropic

Gemma 3 27B

Google

Pricing
Input $/1M$1.00$0.08
Output $/1M$5.00$0.35
Blended $/1M (3:1)$2.00$0.147
RAG example (30K in / 2K out)$0.04$0.0031
Quality & speed
Intelligence Index7.4—
Coding Index43.910.1
Agentic Index80.1
Output speed (tok/s)——
Time to first token——
Specs
Context window200K131K
Input modalitiestext, image, filetext, image

FAQ

Which is cheaper, Claude Haiku 4.5 or Gemma 3 27B?

Gemma 3 27B has the lower blended API price at $0.147 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), Gemma 3 27B costs about $0.0031 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and Gemma 3 27B offers 131K.

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.