Samprix

Claude Haiku 4.5 vs Gemini 3.5 Flash-Lite: API cost

Standard, cached and batch API prices for Claude Haiku 4.5 (Anthropic) and Gemini 3.5 Flash-Lite (Google), and what each costs for your usage.

Prices last checked: how

Gemini 3.5 Flash-Lite is cheaper than Claude Haiku 4.5 at standard rates, with 3.3× cheaper input and 2× cheaper output.

Your usage
Claude Haiku 4.5 / month $78.00 $0.0026 per request
  • Input $30.00
  • Cached input $3.00
  • Output $45.00
Gemini 3.5 Flash-Lite / month $32.40 $0.0011 per request
  • Input $9.00
  • Cached input $0.9
  • Output $22.50
Gemini 3.5 Flash-Lite is cheaper for this usage by $45.60 a month (58% less).

How cost changes with reply length

  • Claude Haiku 4.5
  • Gemini 3.5 Flash-Lite
$0$2$4$602004006008001,000Output tokens per 1,000 input tokensClaude Haiku 4.5Gemini 3.5 Flash-…
Cost of 1,000 requests with 1,000 input tokens each, at standard rates without caching. Hover or use the arrow keys to read values.
Show as a table
Output tokensClaude Haiku 4.5Gemini 3.5 Flash-Lite
0$1.00$0.3
250$2.25$0.93
500$3.50$1.55
750$4.75$2.18
1,000$6.00$2.80

Price per million tokens

Token typeClaude Haiku 4.5Gemini 3.5 Flash-Lite
Input$1$0.30
Cached input$0.10$0.03
Output$5$2.50
Batch input$0.50$0.15
Batch cached input$0.05$0.02
Batch output$2.50$1.25
Standard rates in USD, before tax Claude API pricing Gemini API pricing

Monthly cost for typical workloads

WorkloadClaude Haiku 4.5Gemini 3.5 Flash-Lite
Support chatbot
2,000 in / 300 out tokens, 1,000 requests a day, 50% cached
$78.00$32.40
Document summaries
10,000 in / 800 out tokens, 200 requests a day
$84.00$30.00
Tagging / classifying
400 in / 20 out tokens, 20,000 requests a day
$300.00$102.00
Standard rates in USD, before tax. A month is 30 days.

Or see Claude Haiku 4.5 pricing, Gemini 3.5 Flash-Lite pricing, or compare any two models.

FAQ

Frequently asked questions

Is Claude Haiku 4.5 cheaper than Gemini 3.5 Flash-Lite?

Gemini 3.5 Flash-Lite is cheaper than Claude Haiku 4.5 at standard rates, with 3.3× cheaper input and 2× cheaper output. Based on standard API rates last checked on 30 Sept 2026.

How much do Claude Haiku 4.5 and Gemini 3.5 Flash-Lite cost per million tokens?

Claude Haiku 4.5: $1 per million input tokens and $5 per million output tokens. Gemini 3.5 Flash-Lite: $0.30 input and $2.50 output. These are standard rates in USD, before tax, from each provider’s own pricing page.

Which is cheaper with the Batch API?

Claude Haiku 4.5’s batch rates are $0.50 input and $2.50 output per million tokens (50% off); Gemini 3.5 Flash-Lite’s batch rates are $0.15 input and $1.25 output per million tokens (50% off).

Does prompt caching change the comparison?

Claude Haiku 4.5 charges $0.10 per million cached input tokens, against $1 for normal input; Gemini 3.5 Flash-Lite charges $0.03 per million cached input tokens, against $0.30 for normal input. Cache write and storage charges are extra and aren’t included here.

© 2026 Samprix. Not affiliated with OpenAI, Anthropic or Google.