Comparison
Claude Haiku 4.5 vs GPT-5.4 mini
Claude Haiku 4.5 charges 25% more per input token than GPT-5.4 mini. Output pricing favors GPT-5.4 mini, 10% less per token than Claude Haiku 4.5. GPT-5.4 mini accepts more context per request than Claude Haiku 4.5.
| Field | Claude Haiku 4.5 | GPT-5.4 mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Context window | 200K | 400K |
| Max output | 64K | 128K |
| Input / 1M | $1.00 | $0.7525% cheaper |
| Output / 1M | $5.00 | $4.5010% cheaper |
| Cached input / 1M | $0.10 | $0.07525% cheaper |
| Batch discount | 50% | 50% |
| Release date | 2025-10-01 | 2026-03-17 |
Worked cost examples
Estimated monthly cost on three common usage shapes
| Workload | Claude Haiku 4.5 | GPT-5.4 mini |
|---|---|---|
Chatbot 800 input / 200 output tokens per request, 100,000 requests/month | $180.00 | $150.00cheaper |
RAG pipeline 6,000 input / 700 output tokens per request, 30,000 requests/month | $285.00 | $229.50cheaper |
Batch summarization 20,000 input / 1,500 output tokens per request, 5,000 requests/month | $137.50 | $108.75cheaper |
Claude Haiku 4.5 vs GPT-5.4 mini FAQ
- Is Claude Haiku 4.5 cheaper than GPT-5.4 mini?
- Claude Haiku 4.5 costs $1.00 per 1M input tokens versus $0.75 for GPT-5.4 mini — GPT-5.4 mini is 33% cheaper per input token.
- Which is cheaper for output tokens, Claude Haiku 4.5 or GPT-5.4 mini?
- Claude Haiku 4.5 charges $5.00 per 1M output tokens; GPT-5.4 mini charges $4.50 per 1M output tokens.
- Which has the larger context window, Claude Haiku 4.5 or GPT-5.4 mini?
- GPT-5.4 mini does, with a 400,000-token context window.
- Do Claude Haiku 4.5 and GPT-5.4 mini offer cache pricing?
- Claude Haiku 4.5 discounts cached input to $0.10 per 1M tokens. GPT-5.4 mini discounts cached input to $0.075 per 1M tokens.
Looking for another matchup? See all comparisons.