Prices → Compare → Claude Haiku 4.5 vs Gemini 3.1 Pro
Claude Haiku 4.5 vs Gemini 3.1 Pro: API cost compared
Claude Haiku 4.5 lists at $1.000 in / $5.000 out per 1M tokens. Gemini 3.1 Pro lists at $2.000 in / $12.00. Sticker price only tells you so much — below is what each actually costs across eight production workloads.
Side by side
| Claude Haiku 4.5 | Gemini 3.1 Pro | |
|---|---|---|
| Provider | Anthropic | |
| Input per 1M | $1.000 | $2.000 |
| Output per 1M | $5.000 | $12.00 |
| Cached input per 1M | $0.100 | not published |
| Context window | 200k | 1M |
| Blended per 1M (3:1) | $2.000 | $4.500 |
Monthly cost by workload
Caching applied at each workload's typical hit rate. This is where the two models actually separate.
| Workload | Claude Haiku 4.5 | Gemini 3.1 Pro | Cheaper | Difference |
|---|---|---|---|---|
| Customer support chatbot | $128.90 | $390.00 | Claude Haiku 4.5 | $261.10 (67%) |
| RAG document Q&A | $184.00 | $464.00 | Claude Haiku 4.5 | $280.00 (60%) |
| Coding agent | $92.50 | $344.00 | Claude Haiku 4.5 | $251.50 (73%) |
| Bulk summarization | $1,346 | $2,880 | Claude Haiku 4.5 | $1,534 (53%) |
| Structured data extraction | $1,745 | $5,000 | Claude Haiku 4.5 | $3,255 (65%) |
| Long-form content generation | $214.60 | $520.00 | Claude Haiku 4.5 | $305.40 (59%) |
| Email triage agent | $402.50 | $1,360 | Claude Haiku 4.5 | $957.50 (70%) |
| Translation pipeline | $1,405 | $3,330 | Claude Haiku 4.5 | $1,925 (58%) |
How to read this
Claude Haiku 4.5 is cheaper on the majority of these workloads, but "majority" is not the decision. The output:input price ratio is 5.0 for Claude Haiku 4.5 and 6.0 for Gemini 3.1 Pro. If your traffic is output-heavy — long-form drafting, translation — the model with the lower output price wins regardless of what the input price suggests. If you are input-heavy — RAG, bulk summarization, agents re-reading a codebase — the cached input rate matters more than either headline number.
Cost is also not the only axis. This site does not benchmark quality, latency, or rate limits, and a model that is 3x cheaper but needs two attempts per task is not cheaper. Use these numbers to size a bill, then validate on your own evals.
Run your own numbers
Cost calculator
Enter your own numbers, or start from a workload preset. Costs are monthly and update as you type.
| Model | In /1M | Out /1M | Monthly | vs best |
|---|