o4-mini API pricing
o4-mini costs $1.1 per million input tokens and $4.4 per million output tokens. A typical chatbot request (about 1,500 input + 400 output tokens) costs $0.0034, or $3.41 per 1,000 requests.
0 characters0 words0 tokens (GPT o200k)
| Model | Per month |
|---|---|
| o4-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.
o4-mini price per million tokens
USD, OpenAI standard tier. Prices checked on October 28, 2026.
| Token type | Price per 1M | With Batch API |
|---|---|---|
| Input | $1.1 | $0.55 |
| Cached input | $0.275 | $0.1375 |
| Output | $4.4 | $2.2 |
Model ID: o4-mini · Source: developers.openai.com
What a o4-mini request costs
| Request | Per request | Per 1,000 |
|---|---|---|
| Short chat reply 500 input + 200 output tokens | $0.0014 | $1.43 |
| Chatbot turn with context 1,500 input + 400 output tokens | $0.0034 | $3.41 |
| Document Q&A (RAG) 8,000 input + 500 output tokens | $0.01 | $11.00 |
| Long-document summary 150,000 input + 2,000 output tokens | $0.17 | $174 |
Token counts are measured with GPT's o200k tokenizer and converted for o4-mini (see below). No caching or batch discount.
Similarly priced models
| Model | Chatbot request | vs o4-mini |
|---|---|---|
| GPT-5.4 mini OpenAI | $0.0029 | −14% |
| Grok 4.3 xAI | $0.0030 | −13% |
| Grok 4.20 xAI | $0.0030 | −13% |
| GPT-6.1 Terra OpenAI | $0.0035 | +3% |
| Claude Haiku 4.5 Anthropic | $0.0037 | +7% |
| DeepSeek V4 Pro DeepSeek | $0.0037 | +7% |
Frequently asked questions
How much does the o4-mini API cost?
o4-mini costs $1.1 per million input tokens and $4.4 per million output tokens on OpenAI's standard tier. Prices checked on October 28, 2026.
How much does one o4-mini request cost?
A typical chatbot request with about 1,500 input and 400 output tokens costs about $0.0034, or $3.41 per 1,000 requests. Paste your own prompt into the calculator on this page for an exact estimate.
Does o4-mini support prompt caching?
Yes. Cached input costs $0.275 per million tokens, 75% less than regular input.
Does o4-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 $0.55 / $2.2 per million input / output tokens.
How are o4-mini tokens counted?
o4-mini uses OpenAI's public o200k tokenizer, so its token counts here are exact.