Claude Haiku vs Gemini 1.5 Flash
On a typical agent workload, Gemini 1.5 Flash runs about 91% cheaper than Claude Haiku at list price ($138 against $1,567 a month). Here is the full cost breakdown.
| metric | Claude HaikuAnthropic · Cheap tier | Gemini 1.5 FlashGoogle (Vertex) · Cheap tier |
|---|---|---|
| Input priceper 1M tokens | $0.80 | $0.08 |
| Output priceper 1M tokens | $4.00 | $0.30 |
| Blended price3:1 input:output mix, per 1M | $1.60 | $0.13 |
| One chat request1.5k in / 600 out, no tools | $0.0036 | $0.0003 |
| Agent workload / month2,000 req/day, 3 tool calls, RAG on | $1,567 | $138 |
cheaper · public list prices as of 2026-06 · estimates, not quotes
which_to_choose
Which one should you pick?
On price alone, Gemini 1.5 Flash wins. It comes in around 91% cheaper than Claude Haiku on the same agent workload ($138 against $1,567 a month at 2,000 requests a day), and the gap widens as volume and tool calls grow, because every tool call re-sends the context and you pay for it at each model's rate.
The case for Claude Haiku comes down to fit. If it resolves a task in fewer attempts or shorter prompts on your workload, the higher per-token rate can still come out ahead of a cheaper model that needs retries. Price the two on your own evaluation set and your actual token mix before you commit, because the list price rarely decides it alone.
Claude Haiku: Anthropic's fastest, lowest-cost tier, aimed at high-volume and simpler tasks. Gemini 1.5 Flash: Google's fastest, cheapest tier on Vertex, aimed at high-volume tasks.
faq
Questions & answers
- Is Claude Haiku or Gemini 1.5 Flash cheaper?
- Gemini 1.5 Flash is cheaper at list price. It runs $0.08 per million input tokens and $0.30 per million output tokens, against $0.80 and $4.00 for Claude Haiku. On a typical agent workload that works out to about 91% less per month.
- What is the price difference between Claude Haiku and Gemini 1.5 Flash?
- Claude Haiku is $0.80 in and $4.00 out per million tokens; Gemini 1.5 Flash is $0.08 in and $0.30 out. Output tokens cost several times more than input on both, so the gap that matters most depends on how much your workload generates versus reads.
- Should I switch from Claude Haiku to Gemini 1.5 Flash to cut cost?
- Possibly. Gemini 1.5 Flash is about 91% cheaper on the same workload, and the saving grows with volume and tool calls because each tool call re-sends the context. But a cheaper model that needs retries or longer prompts can cost more in practice, so price both on your own evaluation set and your actual token mix before you switch.
Picking a model is the easy part. Making it cheap in production is the work.
Prompt caching, context trimming, and the right tier per task usually cut an LLM bill by more than switching models. Book a call, or leave your email and I'll reach out.
Prefer proof first? See how this plays out in real case studies →