OpenAI API Cost Calculator
Estimate OpenAI GPT-4o, GPT-4o mini and o-series API costs.
With the default inputs, $0.00750 per request — ~$225.00/month at 1,000 requests/day. Enter your own numbers below to recompute instantly; the full step-by-step math is shown under the worked example.
Results update automatically as you type.
- Input cost
- $0.00250
- Output cost
- $0.00500
- Per request
- $0.00750
- Per day
- $7.50
- Per month
- $225.00
Estimate the cost of the OpenAI API for GPT-4o, GPT-4o mini, and the o-series reasoning models. Enter your token counts and traffic to see per-request and monthly cost, including prompt caching and batch pricing where available.
How this is calculated
Cost per request = (input tokens ÷ 1,000,000 × input price) + (output tokens ÷ 1,000,000 × output price) for your chosen OpenAI model, pulled from our daily-refreshed pricing. Cached input is billed at a reduced rate and batch pricing swaps in the discounted async rate; monthly cost scales the per-request figure by requests per day × 30.
Is this a good result? What to do next
GPT-4o mini is dramatically cheaper than GPT-4o for most tasks, while o-series reasoning models cost more because output (including hidden reasoning tokens) is pricier. Judge the per-request cost against revenue per request, and check the monthly figure against the feature's value.
Typical planning ranges
- GPT-4o mini
- budget tier — cents per 1k requests
- GPT-4o
- mid-tier
- o-series reasoning
- premium output pricing
Ranges are typical planning figures to sanity-check your result, not authoritative benchmarks. Your numbers will vary with use case, volume, and vendor.
How to improve this number
- Route simple requests to GPT-4o mini; reserve GPT-4o/o-series for hard ones.
- Enable prompt caching for a stable system prompt or context.
- Use the batch API for non-real-time jobs.
Common mistakes
- Ignoring that output (and hidden reasoning tokens) cost more than input.
- Estimating with averages when a few large requests skew the bill.
When to use a different approach
To compare OpenAI against Claude, Gemini and others, use the model cost comparison. For a conversation with growing history, use the chatbot cost calculator.
Worked example (defaults)
With the default inputs above, here is the result:
- Input cost
- $0.00250
- Output cost
- $0.00500
- Per request
- $0.00750
- Per day
- $7.50
- Per month
- $225.00
- input: 1,000 / 1e6 x $2.5/M = $0.00250
- output: 500 / 1e6 x $10/M = $0.00500
- monthly = $0.00750 x 1,000 x 30 days
Sources & references
Frequently asked questions
Which OpenAI models are cheapest?+
GPT-4o mini is dramatically cheaper than GPT-4o for most tasks, while o-series reasoning models cost more due to higher output pricing and reasoning tokens.
Does prompt caching lower OpenAI cost?+
Yes. Cached input tokens are billed at a reduced rate, which helps a lot when you reuse a large system prompt or context across requests.
Related calculators
Answering a real question?
This calculator powers these problem-solving guides: