GPT-4o pricing, context window and limits
GPT-4o costs $2.5 per million input tokens and $10 per million output tokens at OpenAI list price. It accepts up to 128,000 tokens of context and returns up to 16,384 tokens.
- Model id
gpt-4o - Snapshot
What does GPT-4o cost?
| Input | $2.5 |
|---|---|
| Output | $10 |
| Cached input (read) | $1.25 |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can GPT-4o read and write?
| Context window | 128,000 |
|---|---|
| Max output | 16,384 |
What can GPT-4o do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | No |
| Input | text, image, pdf |
| Output | text |
What does a request to GPT-4o cost?
| A typical request: 1,000 tokens in, 500 out | $0.0075 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.035 |
| 1,000 typical requests | $7.5 |
| 1 million tokens in and 1 million out | $12.5 |
Input read from the provider's prompt cache costs $1.25 per million tokens instead of $2.5, 50% less. A request that repeats a 1,000-token prompt from the cache costs $0.0063 instead of $0.0075.
Among 49 OpenAI models with a published price, GPT-4o is the 28th cheapest by input price. Its context window is the 34th largest of 48. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call GPT-4o through DVARA?
Configure the openai provider in the DVARA LLM Gateway and send the model id gpt-4o. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other OpenAI models are there?
- GPT-4.1 nano$0.1 in · $0.4 out · 1.05M context
- GPT-4o (2024-05-13)$5 in · $15 out · 128K context
- GPT-4.1 mini$0.4 in · $1.6 out · 1.05M context
- GPT-4o (2024-08-06)$2.5 in · $10 out · 128K context
- GPT-4.1$2 in · $8 out · 1.05M context
- GPT-4o (2024-11-20)$2.5 in · $10 out · 128K context
- GPT-4 Turbo$10 in · $30 out · 128K context
- GPT-4o mini$0.15 in · $0.6 out · 128K context
- GPT-4$30 in · $60 out · 8K context
- GPT-5$1.25 in · $10 out · 400K context
- GPT-3.5-turbo$0.5 in · $1.5 out · 16K context
- GPT-5 Mini$0.25 in · $2 out · 400K context
Which models from other providers are similar to GPT-4o?
These are the closest in context window and input price, one per provider.
- Command A PlusCohere · $2.5 in · $10 out · 128K context
- Palmyra X4 (US)Amazon Bedrock · $2.5 in · $10 out · 123K context
- Qwen2.5-VL 72B InstructAlibaba Qwen · $2.294 in · $6.881 out · 131K context
- Pixtral Large (latest)Mistral AI · $2 in · $6 out · 128K context
- Deep Research Max Preview (Apr-21-2026)Google Gemini · $2 in · $12 out · 131K context