Claude Haiku 4.5 vs Gemini 3.8 Flash: which API costs less?
Averaged across three realistic workloads, Gemini 3.8 Flash is about 25% cheaper than Claude Haiku 4.5. Below: raw rates and side-by-side monthly costs, computed from prices verified 2026-10-17 (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 3.8 FlashGoogle | $0.750 | $3.75 | $0.075 |
Claude Haiku 4.5: Previous generation; Haiku 5.5 is 10x cheaper. Gemini 3.8 Flash: Launch price until Dec 31, 2026; $1.50/$7.50 announced from Jan 1, 2027.
Monthly cost, side by side
| Workload | Claude Haiku 4.5 | Gemini 3.8 Flash | Difference |
|---|---|---|---|
Customer-support chatbot 2M input + 0.5M output tokens/month, 60% of input served from prompt cache | $3.42 | $2.56 | Gemini 3.8 Flash −25% |
RAG / document Q&A 20M input + 1M output tokens/month, 70% cached (shared context) | $12.40 | $9.30 | Gemini 3.8 Flash −25% |
Agentic coding assistant 50M input + 5M output tokens/month, 80% cached (long sessions) | $39.00 | $29.25 | Gemini 3.8 Flash −25% |
Your traffic looks different? Run your own numbers in the calculator.
FAQ
Which is cheaper: Claude Haiku 4.5 or Gemini 3.8 Flash?
Across three realistic workloads (chatbot, RAG, agent), Gemini 3.8 Flash works out about 25% cheaper than Claude Haiku 4.5 on average. Raw rates: Claude Haiku 4.5 $1/$5 per 1M tokens vs Gemini 3.8 Flash $0.750/$3.75. Verified 2026-10-17.
Does prompt caching change the comparison?
Yes — cached input costs $0.100 on Claude Haiku 4.5 and $0.075 on Gemini 3.8 Flash. 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.