Claude Haiku 4.5 vs Gemini 3.5 Flash: which API costs less?
Averaged across three realistic workloads, Claude Haiku 4.5 is about 67% cheaper than Gemini 3.5 Flash. Below: raw rates and side-by-side monthly costs, computed from prices verified 2026-07-05 (we track what you are billed today, promos included).
Rates per 1M tokens
| Model | Input | Output | Cached input |
|---|---|---|---|
| Claude Haiku 4.5Anthropic | $1 | $5 | $0.100 |
| Gemini 3.5 FlashGoogle | $1.50 | $9 | — |
Monthly cost, side by side
| Workload | Claude Haiku 4.5 | Gemini 3.5 Flash | Difference |
|---|---|---|---|
Customer-support chatbot 2M input + 0.5M output tokens/month, 60% of input served from prompt cache | $3.42 | $7.50 | Claude Haiku 4.5 −54% |
RAG / document Q&A 20M input + 1M output tokens/month, 70% cached (shared context) | $12.40 | $39.00 | Claude Haiku 4.5 −68% |
Agentic coding assistant 50M input + 5M output tokens/month, 80% cached (long sessions) | $39.00 | $120 | Claude Haiku 4.5 −68% |
Your traffic looks different? Run your own numbers in the calculator.
FAQ
Which is cheaper: Claude Haiku 4.5 or Gemini 3.5 Flash?
Across three realistic workloads (chatbot, RAG, agent), Claude Haiku 4.5 works out about 67% cheaper than Gemini 3.5 Flash on average. Raw rates: Claude Haiku 4.5 $1/$5 per 1M tokens vs Gemini 3.5 Flash $1.50/$9. Verified 2026-07-05.
Does prompt caching change the comparison?
Yes — cached input costs $0.100 on Claude Haiku 4.5 and the full input rate on Gemini 3.5 Flash (no cache discount listed). Our scenario numbers already include realistic cache hit rates.
Is cheaper always better?
No. Price is one axis — model capability, context window and latency differ. This page answers only the cost question; benchmark quality on your own tasks before switching.