How much does GPT-4o cost per API call?

GPT-4o costs $2.50 per million input tokens and $10.00 per million output tokens. A typical 1K input + 500 output request costs about $0.0075. GPT-4o mini is much cheaper at $0.15 input / $0.60 output per million tokens.

Does OpenAI charge for cached tokens?

Yes, but at a discount. OpenAI offers prompt caching for inputs longer than 1,024 tokens. Cached tokens are billed at 50% of the normal input rate for GPT-4o, reducing costs for repeated system prompts.

How can I reduce OpenAI API costs?

Switch to GPT-4o mini for tasks that do not require GPT-4o quality. Use prompt caching for repeated system prompts. Reduce output token limits where possible. Batch requests using the OpenAI Batch API for a 50% discount.

OpenAI API Cost Calculator

Calculate GPT-4o, GPT-4 Turbo, and GPT-3.5 API costs.

Model

Input text

0 input tokens detectedOutput estimated at 50% (0 tokens)

Model pricing

Input price$0.000003 / token$2.50 / 1M tokens

Output price$0.000010 / token$10.00 / 1M tokens

Cost estimate

Per request$0.000000

Per 1K requests$0.000000

Daily (100 req)$0.000000

Monthly est.$0.000000

0 input tokens0 output tokens

Related Tools

GPTOpenAI Token CounterNEW

Count tokens for GPT-4o, GPT-4 Turbo, and GPT-3.5 models.

GPTOpenAI Context Window CalculatorNEW

Check if your prompts fit within GPT-4o and GPT-3.5 context windows.

CSTAI API Cost CalculatorNEW

Estimate AI API costs for GPT, Claude, Gemini, and LLaMA.

CLDClaude API Cost CalculatorNEW

Calculate Anthropic Claude API costs for Sonnet, Opus, and Haiku.

FAQ

How much does GPT-4o cost per API call?: GPT-4o costs $2.50 per million input tokens and $10.00 per million output tokens. A typical 1K input + 500 output request costs about $0.0075. GPT-4o mini is much cheaper at $0.15 input / $0.60 output per million tokens.
Does OpenAI charge for cached tokens?: Yes, but at a discount. OpenAI offers prompt caching for inputs longer than 1,024 tokens. Cached tokens are billed at 50% of the normal input rate for GPT-4o, reducing costs for repeated system prompts.
How can I reduce OpenAI API costs?: Switch to GPT-4o mini for tasks that do not require GPT-4o quality. Use prompt caching for repeated system prompts. Reduce output token limits where possible. Batch requests using the OpenAI Batch API for a 50% discount.

Estimate OpenAI API costs for GPT-4o, GPT-4o mini, GPT-4 Turbo, and GPT-3.5 Turbo. Paste text to auto-count tokens or enter token counts manually. See per-request, per-1K, daily, and monthly cost breakdowns.