Comparison
Claude Haiku 4.5 vs Gemini 3.5 Flash
Per input token, Claude Haiku 4.5 runs 33% cheaper than Gemini 3.5 Flash. On generated (output) tokens, Gemini 3.5 Flash costs 44% more than Claude Haiku 4.5. Gemini 3.5 Flash accepts more context per request than Claude Haiku 4.5.
| Field | Claude Haiku 4.5 | Gemini 3.5 Flash |
|---|---|---|
| Provider | Anthropic | |
| Context window | 200K | 1M |
| Max output | 64K | 65.5K |
| Input / 1M | $1.0033% cheaper | $1.50 |
| Output / 1M | $5.0044% cheaper | $9.00 |
| Cached input / 1M | $0.1033% cheaper | $0.15 |
| Batch discount | 50% | 50% |
| Release date | 2025-10-01 | — |
Worked cost examples
Estimated monthly cost on three common usage shapes
| Workload | Claude Haiku 4.5 | Gemini 3.5 Flash |
|---|---|---|
Chatbot 800 input / 200 output tokens per request, 100,000 requests/month | $180.00cheaper | $300.00 |
RAG pipeline 6,000 input / 700 output tokens per request, 30,000 requests/month | $285.00cheaper | $459.00 |
Batch summarization 20,000 input / 1,500 output tokens per request, 5,000 requests/month | $137.50cheaper | $217.50 |
Claude Haiku 4.5 vs Gemini 3.5 Flash FAQ
- Is Claude Haiku 4.5 cheaper than Gemini 3.5 Flash?
- Claude Haiku 4.5 costs $1.00 per 1M input tokens versus $1.50 for Gemini 3.5 Flash — Claude Haiku 4.5 is 33% cheaper per input token.
- Which is cheaper for output tokens, Claude Haiku 4.5 or Gemini 3.5 Flash?
- Claude Haiku 4.5 charges $5.00 per 1M output tokens; Gemini 3.5 Flash charges $9.00 per 1M output tokens.
- Which has the larger context window, Claude Haiku 4.5 or Gemini 3.5 Flash?
- Gemini 3.5 Flash does, with a 1,048,576-token context window.
- Do Claude Haiku 4.5 and Gemini 3.5 Flash offer cache pricing?
- Claude Haiku 4.5 discounts cached input to $0.10 per 1M tokens. Gemini 3.5 Flash discounts cached input to $0.15 per 1M tokens.
Looking for another matchup? See all comparisons.