Gemini 3.5 Flash vs Claude Haiku 4.5: token pricing & cost compared (July 2026)

How Gemini 3.5 Flash (Google) and Claude Haiku 4.5 (Anthropic) actually compare on price — input, output, and total monthly cost at the MAU you care about. Updated against live OpenRouter pricing.

Google

Gemini 3.5 Flash

Input: $1.50 / 1M tokens
Output: $9.00 / 1M tokens
Output / Input ratio: 6.0×
Context window: 1,048.576K

Anthropic

Claude Haiku 4.5

Input: $1.00 / 1M tokens
Output: $5.00 / 1M tokens
Output / Input ratio: 5.0×
Context window: 200K

The short answer

Claude Haiku 4.5 is cheaper across the board for typical workloads.

Token pricing side-by-side

Gemini 3.5 Flash
Claude Haiku 4.5

Cost at your usage

Avg input tokens / call

Avg output tokens / call

Calls per active user / day: 5

Active days / month: 20

MAU: 1,000

Gemini 3.5 Flash

Per call

$0.00525

Per user / mo

$0.5250

Total / mo

$525

Claude Haiku 4.5

Per call

$0.00300

Per user / mo

$0.3000

Total / mo

$300

Claude Haiku 4.5 is cheaper by $0.2250/user/month — a saving of $225/month at 1,000 MAU.

Total monthly bill across MAU

Gemini 3.5 Flash
Claude Haiku 4.5

Same usage profile applied to both models; only the per-token price differs.

Run this against your real numbers

The mini-calculator above is a preview. Use the full tools to model power-user blast radius, gross margin, and 12-month spend forecasts.

Other comparisons

Gemini 3.5 Flash vs GPT-4o mini DeepSeek V4 Flash vs Gemini 3.5 Flash GPT-4o mini vs Claude Haiku 4.5 Claude Haiku 4.5 vs Gemini 2.5 Flash Claude 3.7 Sonnet vs Claude Haiku 4.5 Claude Haiku 4.5 vs Claude 3.5 Haiku

Comparing Gemini 3.5 Flash vs Claude Haiku 4.5 on price alone never tells the whole story — output-token weighting, context length, and your usage profile change the answer dramatically. Use the calculators below for the full picture.