GPT-4o
OpenAI's first natively multimodal model, positioned as a balanced mid-range option.
Key Specifications
- Context window
- 128K tokens
- Max output
- 16K tokens
- Knowledge cutoff
- web search available
- Released
- Inputs
- Text, image
- Capabilities Show details
- Function calling Connect to external tools, APIs, and systems. Structured output Return responses in structured formats like JSON. Web search Search the web for up-to-date information. Code execution Write and execute code in a sandboxed environment. File upload Process uploaded documents, spreadsheets, and other files. MCP Connect to services via Model Context Protocol. Image generation Generate and edit images from text prompts.
Hosted API pricing
| Provider | Input /1M tokens | Output /1M tokens | Cached input /1M | Cost at 10M in + 2M out | |
|---|---|---|---|---|---|
|
|
$2.50 | $10.00 | $1.25 | $45.00 | View |
|
|
$2.50 | $10.00 | $1.25 | $45.00 | View |
|
|
$2.50 | $10.00 | $1.25 | $45.00 | View |
|
|
$2.50 | $10.00 | $45.00 | View |
Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.
Similarly priced models
The models nearest GPT-4o by blended rate, each at its own cheapest provider.
| Model | Blended /1M | Input /1M | Output /1M | Context | Cutoff | vs GPT-4o |
|---|---|---|---|---|---|---|
|
|
$3.6667 | $2.00 | $12.00 | 1M | Jan 2025 | −2% |
|
|
$3.6667 | $2.00 | $12.00 | 1M | Feb 2026 | −2% |
|
|
$3.6667 | $2.00 | $12.00 | 1M | −2% | |
|
|
$3.75 | $2.50 | $10.00 | 256K | 0% | |
|
|
$3.75 | $2.50 | $10.00 | 128K | Feb 2023 | 0% |
|
|
$3.75 | $2.50 | $10.00 | 128K | Oct 2023 | |
|
|
$3.7917 | $1.75 | $14.00 | 400K | Aug 2025 | +1% |
|
|
$3.7917 | $1.75 | $14.00 | 400K | Aug 2025 | +1% |
|
|
$4.5833 | $2.50 | $15.00 | 1M | Aug 2025 | +22% |
|
|
$5.00 | $3.00 | $15.00 | 200K | Jan 2025 | +33% |
|
|
$5.00 | $3.00 | $15.00 | 1M | Aug 2025 | +33% |
Prices are USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.
Frequently Asked Questions
What is GPT-4o good for?
General text and image tasks with OpenAI's hosted tools. OpenAI calls it a versatile general-purpose model, mid-priced in its lineup.
When is GPT-4o not a good fit?
Audio or video input, extended reasoning, and anything needing recent knowledge. The GPT-4.1 and GPT-5 families take far longer inputs, and closed weights rule out self-hosting.
What is the cheapest way to run GPT-4o?
The cheapest hosted rate is $2.50 / $10.00 per 1M tokens via OpenAI.
Can I self-host GPT-4o?
No. OpenAI does not publish the weights; GPT-4o is available only through hosted APIs.
More from OpenAI
| Model | Context | Input /1M | Output /1M |
|---|---|---|---|
|
|
400K | $1.75 | $14.00 |
|
|
400K | $1.75 | $14.00 |
|
|
1M | $2.00 | $12.00 |
|
|
1M | $2.00 | $10.00 |
|
|
1M | $2.50 | $15.00 |
|
|
1M | $2.00 | $8.00 |
|
|
200K | $2.00 | $8.00 |
|
|
400K | $1.25 | $10.00 |