Claude Haiku 5.5 vs Gemini 3.8 Flash: cost comparison

For a typical chatbot reply, Claude Haiku 5.5 is 5.8× cheaper than Gemini 3.8 Flash ($0.455 vs $2.62 per 1,000 replies, including Claude's ~30% higher token count).

Scheduled price change: Gemini 3.8 Flash: Introductory price through Dec 31, 2026; $1.50 input / $7.50 output from Jan 1, 2027.

Claude Haiku 5.5 Anthropic

$0.10input /1M

$0.01cached /1M

$0.50output /1M

Prompts over 100,000 tokens are billed at $0.50 input / $0.05 cached / $2.50 output per 1M tokens for the whole request.
Uses Anthropic's newer tokenizer, which produces about 30% more tokens for the same text than Claude Sonnet 4.6 and earlier.
Batch processing: 50% off input and output ($0.05 / $0.25 per 1M tokens).

Gemini 3.8 Flash Google

$0.75input /1M

$0.075cached /1M

$3.75output /1M

Introductory price through Dec 31, 2026; $1.50 input / $7.50 output from Jan 1, 2027.
Batch processing: 50% off input and output ($0.375 / $1.875 per 1M tokens).

Cost per 1,000 requests

Workload	Claude Haiku 5.5	Gemini 3.8 Flash	Difference
Chatbot reply1,500 input / 400 output tokens	$0.455	$2.62	5.8×
RAG answer8,000 input / 600 output tokens	$1.43	$8.25	5.8×
Agent step30,000 input (80% cached) / 800 output	$1.61	$9.30	5.8×
Summarize a long report60,000 input / 1,200 output tokens	$8.58	$49.50	5.8×
Classify a ticket400 input / 10 output tokens	$0.0585	$0.337	5.8×

Standard pricing, no batch discount. Claude 4.7+ costs include its ~30% higher token count for the same text. Price is only one factor; quality, speed, context length and rate limits matter too, so test both on your own prompts.

Run your own numbers in the calculator →

More comparisons

More free tools from us

CleanStatement →

Convert bank and credit card statement PDFs to Excel or CSV. Runs in your browser; the file is never uploaded.

FillDesk →

Answer vendor security questionnaires from your own answer library and export to Word or Excel.