Claude Haiku 4.5 vs Gemini 2.5 Flash — LLM API Cost Comparison
Compare Claude Haiku 4.5 (Anthropic) vs Gemini 2.5 Flash (Google) on cost per million tokens, context window, and monthly spend.
Prices verified 2026-05-20 · Pricing may change — use the calculator for current estimates
- Input
- $1/1M tokens
- Output
- $5/1M tokens
- Context
- 200K tokens
- Released
- 2025-10
Fastest Anthropic model; near-frontier intelligence
- Input
- $0.3/1M tokens
- Output
- $2.5/1M tokens
- Context
- 1M tokens
- Released
- 2025-09
Hybrid reasoning; 1M context with thinking budgets
Monthly Cost by Usage Tier (70% input / 30% output ratio)
| Usage | Claude Haiku 4.5 | Gemini 2.5 Flash | Cheaper by |
|---|---|---|---|
| Light (1M tokens) | $2.20 | $0.960 | Gemini 2.5 Flash (56%) |
| Moderate (10M tokens) | $22.00 | $9.60 | Gemini 2.5 Flash (56%) |
| Heavy (100M tokens) | $220 | $96.00 | Gemini 2.5 Flash (56%) |
| Very Heavy (1B tokens) | $2,200 | $960 | Gemini 2.5 Flash (56%) |
Frequently Asked Questions
Which is cheaper — Claude Haiku 4.5 or Gemini 2.5 Flash?
For input tokens, Gemini 2.5 Flash is cheaper at $0.3/1M tokens — 3.3× less than $1/1M. For output tokens, Gemini 2.5 Flash wins at $2.5/1M 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 2.5 Flash?
Claude Haiku 4.5 supports 200,000 tokens per request; Gemini 2.5 Flash supports 1,000,000 tokens. Gemini 2.5 Flash 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 2.5 Flash?
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 2.5 Flash (Google) if Hybrid reasoning; 1M context with thinking budgets. 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 2.5 Flash?
At 700M input + 300M output tokens (1B total): Claude Haiku 4.5 costs $2200; Gemini 2.5 Flash costs $960. The difference is $1240/billion tokens at this 70/30 input/output ratio.