Samprix

Claude Haiku 4.5 vs Gemini 3.8 Flash: API cost

Standard, cached and batch API prices for Claude Haiku 4.5 (Anthropic) and Gemini 3.8 Flash (Google), and what each costs for your usage.

Prices last checked: how

Gemini 3.8 Flash is cheaper than Claude Haiku 4.5 at standard rates, with 25% cheaper input and 25% 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 3.8 Flash / month $58.50 $0.002 per request
  • Input $22.50
  • Cached input $2.25
  • Output $33.75
Gemini 3.8 Flash is cheaper for this usage by $19.50 a month (25% less).

How cost changes with reply length

  • Claude Haiku 4.5
  • Gemini 3.8 Flash
$0$2$4$602004006008001,000Output tokens per 1,000 input tokensClaude Haiku 4.5Gemini 3.8 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 3.8 Flash
0$1.00$0.75
250$2.25$1.69
500$3.50$2.63
750$4.75$3.56
1,000$6.00$4.50

Price per million tokens

Token typeClaude Haiku 4.5Gemini 3.8 Flash
Input$1$0.75
Cached input$0.10$0.075
Output$5$3.75
Batch input$0.50$0.375
Batch cached input$0.05$0.0375
Batch output$2.50$1.875

Gemini 3.8 Flash: promotional price until 31 Dec 2026.

Standard rates in USD, before tax Claude API pricing Gemini API pricing

Monthly cost for typical workloads

WorkloadClaude Haiku 4.5Gemini 3.8 Flash
Support chatbot
2,000 in / 300 out tokens, 1,000 requests a day, 50% cached
$78.00$58.50
Document summaries
10,000 in / 800 out tokens, 200 requests a day
$84.00$63.00
Tagging / classifying
400 in / 20 out tokens, 20,000 requests a day
$300.00$225.00
Standard rates in USD, before tax. A month is 30 days.

Or see Claude Haiku 4.5 pricing, Gemini 3.8 Flash pricing, or compare any two models.

FAQ

Frequently asked questions

Is Claude Haiku 4.5 cheaper than Gemini 3.8 Flash?

Gemini 3.8 Flash is cheaper than Claude Haiku 4.5 at standard rates, with 25% cheaper input and 25% cheaper output. Based on standard API rates last checked on 30 Sept 2026.

How much do Claude Haiku 4.5 and Gemini 3.8 Flash cost per million tokens?

Claude Haiku 4.5: $1 per million input tokens and $5 per million output tokens. Gemini 3.8 Flash: $0.75 input and $3.75 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 3.8 Flash’s batch rates are $0.375 input and $1.875 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 3.8 Flash charges $0.075 per million cached input tokens, against $0.75 for normal input. Cache write and storage charges are extra and aren’t included here.

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