GPT-4o mini API pricing
GPT-4o mini costs $0.15 per million input tokens and $0.6 per million output tokens. A typical chatbot request (about 1,500 input + 400 output tokens) costs $0.00047, or $0.47 per 1,000 requests.
0 characters0 words0 tokens (GPT o200k)
| Model | Per month |
|---|---|
| GPT-4o mini |
≈ = estimated token count: only OpenAI publishes its tokenizer. Claude counts use Anthropic’s published ratios; use the count_tokens API for an exact number.
GPT-4o mini price per million tokens
USD, OpenAI standard tier. Prices checked on October 28, 2026.
| Token type | Price per 1M | With Batch API |
|---|---|---|
| Input | $0.15 | $0.075 |
| Cached input | $0.075 | $0.0375 |
| Output | $0.6 | $0.3 |
Model ID: gpt-4o-mini · Source: developers.openai.com
What a GPT-4o mini request costs
| Request | Per request | Per 1,000 |
|---|---|---|
| Short chat reply 500 input + 200 output tokens | $0.00019 | $0.20 |
| Chatbot turn with context 1,500 input + 400 output tokens | $0.00047 | $0.47 |
| Document Q&A (RAG) 8,000 input + 500 output tokens | $0.0015 | $1.50 |
| Long-document summary 150,000 input + 2,000 output tokens | $0.02 | $23.70 |
Token counts are measured with GPT's o200k tokenizer and converted for GPT-4o mini (see below). No caching or batch discount.
Similarly priced models
| Model | Chatbot request | vs GPT-4o mini |
|---|---|---|
| Gemini 2.5 Flash-Lite Google | $0.00032 | −32% |
| GPT-6 Luna OpenAI | $0.00035 | −25% |
| Claude Haiku 5.5 Anthropic | $0.00041 | −11% |
| GPT-5.6 Luna OpenAI | $0.00078 | +68% |
| GPT-5.4 nano OpenAI | $0.00080 | +72% |
| DeepSeek Flash DeepSeek | $0.00095 | +105% |
Frequently asked questions
How much does the GPT-4o mini API cost?
GPT-4o mini costs $0.15 per million input tokens and $0.6 per million output tokens on OpenAI's standard tier. Prices checked on October 28, 2026.
How much does one GPT-4o mini request cost?
A typical chatbot request with about 1,500 input and 400 output tokens costs about $0.00047, or $0.47 per 1,000 requests. Paste your own prompt into the calculator on this page for an exact estimate.
Does GPT-4o mini support prompt caching?
Yes. Cached input costs $0.075 per million tokens, 50% less than regular input.
Does GPT-4o mini have a Batch API discount?
Yes: 50% off for requests sent through the Batch API, which may take up to 24 hours. That makes it $0.075 / $0.3 per million input / output tokens.
How are GPT-4o mini tokens counted?
GPT-4o mini uses OpenAI's public o200k tokenizer, so its token counts here are exact.