Back to models
GPT-5.4 nano vs Claude Haiku 4.5
GPT-5.4 nano and Claude Haiku 4.5: current price, context, max output, and supported operations.
Pricing comparison
| GPT-5.4 nano | Claude Haiku 4.5 | |
|---|---|---|
| Model maker | OpenAI | Anthropic |
| Delivery availability | Available | Available |
| Context window | 400K | 200K |
| Max output | 128K | 64K |
| Official price | Input$0.20per 1M tokensOutput$1.25per 1M tokens | Input$1.00per 1M tokensOutput$5.00per 1M tokens |
| Verified price | Input$0.14per 1M tokensOutput$0.875per 1M tokens | Input$0.30per 1M tokensOutput$1.50per 1M tokens |
| Model performance |
|
|
| Capabilities | Prompt CacheTool useVision | JSON modePrompt CacheReasoningTool useVision |
Summary
- GPT-5.4 nano: Input $0.14 / Output $0.875 per 1M tokens; Claude Haiku 4.5: Input $0.30 / Output $1.50 per 1M tokens. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
- GPT-5.4 nano has a 2.0x larger context window
- GPT-5.4 nano supports 2.0x more output tokens
FAQ
Which is cheaper, GPT-5.4 nano or Claude Haiku 4.5?
GPT-5.4 nano: Input $0.14 / Output $0.875 per 1M tokens; Claude Haiku 4.5: Input $0.30 / Output $1.50 per 1M tokens. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
What are the key differences between GPT-5.4 nano and Claude Haiku 4.5?
Claude Haiku 4.5: JSON mode, Reasoning