GPT-4o API Cost Calculator
GPT-4o costs $2.5 per 1M input tokens and $10 per 1M output tokens at official OpenAI API prices, verified 2026-10-26. Estimate your own usage below — the calculator is preset to this model.
Calculate your GPT-4o cost →Paste text to count tokens instead
Cost per call
—
Estimated monthly cost
—
Official price vs gateway price
| Where | Input / 1M | Output / 1M |
|---|---|---|
| Official API | $2.5 | $10 |
GPT-4o is priced above at the official list rate. We have not found a gateway that sells it cheaper with a verifiable public price, so no gateway row is shown — we never estimate one.
Using open-weight models instead (DeepSeek, Qwen, Llama, gpt-oss)? See our Novita AI gateway prices, or go toNovita AI (affiliate).Disclosure.
OpenAI lists GPT-4o as Deprecated; still available at listed Standard/Batch rates.
GPT-4o price facts
| Input | $2.5 per 1M tokens |
|---|---|
| Output | $10 per 1M tokens |
| Cached input | $1.25 per 1M tokens |
| Batch tier | $1.25 in / $5 out per 1M tokens |
| Context window | 128,000 tokens |
| Released | 2024-08-06 |
| Price verified | 2026-10-26 · source |
What GPT-4o costs in practice
| Workload | Per call | Per month |
|---|---|---|
| Chat assistant 2,000 input / 500 output tokens per call, 10,000 calls a month | $0.01 | $100.00 |
| Document processing 50,000 input / 2,000 output tokens per call, 1,000 calls a month | $0.145 | $145.00 |
| Agent loop with prompt caching 10,000 fresh input / 100,000 cached input / 2,000 output tokens per call, 500 calls a month | $0.17 | $85.00 |
Frequently asked questions
How much does GPT-4o cost per month?
It depends entirely on token volume. As worked examples: a chat assistant doing 10,000 calls a month costs $100.00, while a document pipeline doing 1,000 long calls costs $145.00. Use the calculator on this page with your own numbers for an exact figure. Prices are official rates verified 2026-10-26.
Is GPT-4o cheaper than GPT-6 Luna?
At a blended workload of 1M input and 250K output tokens, GPT-4o costs $5.00 and GPT-6 Luna costs $0.225 — so GPT-6 Luna is cheaper at this mix. The answer can flip if your workload is mostly output or mostly cached input.
Does GPT-4o have batch or caching discounts?
Yes — batch processing is $1.25 / $5 per 1M tokens. Cached input is billed at $1.25 per 1M tokens. Prices verified 2026-10-26. We do not invent unpublished rates.
Are these official prices or gateway prices?
GPT-4o on this page uses official OpenAI API prices from the provider's public pricing page. Gateway reseller rates, when shown elsewhere on the site, are labeled separately.
Related
- All OpenAI API prices
- GPT-6 Astra cost calculator
- GPT-6.1 Sol cost calculator
- GPT-6.1 Terra cost calculator
- GPT-6 Luna cost calculator
- GPT-6 Sol cost calculator
- GPT-5.6 Sol cost calculator
- GPT-5.6 Terra cost calculator
- GPT-5.6 Luna cost calculator
- GPT-5 Mini cost calculator
- GPT-4o Mini cost calculator
- GPT-4.1 cost calculator
- GPT-4.1 Mini cost calculator
- chat-latest (ChatGPT Instant) cost calculator
Related models
Closest in cost for 1M input + 250K output tokens (standard tier), listed by price.
- Claude Sonnet 5.5 — $2 / $10 per 1M tokens ($4.50 for that workload)
- Gemini 4 Argon — $2 / $10 per 1M tokens ($4.50 for that workload)
- Claude Sonnet 5 — $2 / $10 per 1M tokens ($4.50 for that workload)
- Gemini 3.1 Pro — $2 / $12 per 1M tokens ($5.00 for that workload)