LLM Cost Calculator

Claude Haiku 4.5 vs Gemini 3.1 Flash-Lite — LLM API Cost Comparison

Compare Claude Haiku 4.5 (Anthropic) vs Gemini 3.1 Flash-Lite (Google) on cost per million tokens, context window, and monthly spend.

Prices verified 2026-05-23 · Pricing may change — use the calculator for current estimates

Anthropic
Claude Haiku 4.5
Current
Input
$1/1M tokens
Output
$5/1M tokens
Context
200K tokens
Released
2025-10

Fastest Anthropic model; near-frontier intelligence

Google
Gemini 3.1 Flash-Lite
Current
Input
$0.25/1M tokens
Output
$1.5/1M tokens
Context
1M tokens
Released
2026-04

Most cost-efficient Gemini; high-volume agentic tasks

Monthly Cost by Usage Tier (70% input / 30% output ratio)

UsageClaude Haiku 4.5Gemini 3.1 Flash-LiteCheaper by
Light (1M tokens)$2.20$0.625Gemini 3.1 Flash-Lite (72%)
Moderate (10M tokens)$22.00$6.25Gemini 3.1 Flash-Lite (72%)
Heavy (100M tokens)$220$62.50Gemini 3.1 Flash-Lite (72%)
Very Heavy (1B tokens)$2,200$625Gemini 3.1 Flash-Lite (72%)

Frequently Asked Questions

Which is cheaper — Claude Haiku 4.5 or Gemini 3.1 Flash-Lite?

For input tokens, Gemini 3.1 Flash-Lite is cheaper at $0.25/1M tokens — 4.0× less than $1/1M. For output tokens, Gemini 3.1 Flash-Lite wins at $1.5/1M vs $5/1M. At heavy workloads (100M tokens/month), the cost difference can be significant.

What is the context window difference between Claude Haiku 4.5 and Gemini 3.1 Flash-Lite?

Claude Haiku 4.5 supports 200,000 tokens per request; Gemini 3.1 Flash-Lite supports 1,000,000 tokens. Gemini 3.1 Flash-Lite wins on context length, making it better for long documents, large codebases, or extended conversations without chunking.

When should I choose Claude Haiku 4.5 over Gemini 3.1 Flash-Lite?

Choose Claude Haiku 4.5 (Anthropic) if you prefer Anthropic's ecosystem, tooling, or reliability track record. Fastest Anthropic model; near-frontier intelligence. Choose Gemini 3.1 Flash-Lite (Google) if Most cost-efficient Gemini; high-volume agentic tasks. the price/performance fits your workload better. Use this calculator to find the break-even point for your exact token volume.

How much does 1 billion tokens cost on Claude Haiku 4.5 vs Gemini 3.1 Flash-Lite?

At 700M input + 300M output tokens (1B total): Claude Haiku 4.5 costs $2200; Gemini 3.1 Flash-Lite costs $625. The difference is $1575/billion tokens at this 70/30 input/output ratio.