GPT-4o
Featured Latest OpenAI GPT-4o Generally Available May 2024
OpenAI's flagship omni-modal model. Fast, multimodal (text, vision, audio), 128K context, and strong across reasoning, coding, and instruction following.
Context
128K
tokens
Input
$2.50
per MTok
Output
$10.00
per MTok
About
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...
Modalities
Input
Text Vision Audio Documents / PDFs Code
Output
Text Code Audio
Code Examples
curl https://api.openai.com/v1/chat/completions \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o",
"messages": [
{ "role": "user", "content": "Explain quantum entanglement in one sentence." }
]
}' API Parameters
| Name | Type | Description |
|---|---|---|
frequency_penalty | number | Penalize tokens by their frequency so far. Positive values reduce repetition. |
logit_bias | object | Map of token-id to bias (-100…100) added to the logit before sampling. |
logprobs | boolean | Return log probabilities for each output token. |
max_completion_tokens | integer | Maximum number of tokens the model may generate in the response. |
max_tokens deprecated | integer | Deprecated. Use max_completion_tokens. |
presence_penalty | number | Penalize tokens that have appeared at all so far. Positive values encourage new topics. |
response_format | one of | Constrain output to a JSON schema or an enum (structured outputs). |
seed | integer | Deterministic seed for sampling. Same seed + same prompt produces identical output. |
stop | array | Up to 4 sequences where the API will stop generating tokens. |
structured_outputs | boolean | Enable JSON-schema-constrained output. |
temperature | number | Sampling temperature; higher values produce more random output. 0 is deterministic. |
tool_choice | one of | Controls which (if any) tool is called: "none", "auto", "required", or a specific tool. |
tools | array | List of tools (functions) the model may call. |
top_logprobs | integer | Return the top-N most likely tokens at each step (requires logprobs: true). |
top_p | number | Nucleus sampling: consider only tokens whose cumulative probability ≥ top_p. |
web_search_options | object | Configuration for web-search tool augmentation. |
Standard OpenAI-compatible parameters. Consult the provider docs for model-specific behaviour.
Benchmark Scores
| Benchmark | Score |
|---|---|
| MMLU | 88.7% |
| HumanEval | 90.2% |
| MATH | 76.6% |
| GPQA Diamond | 53.6% |
Performance
110
tok / sec
output speed
Source: Artificial Analysis, April 2026
Strengths & Limitations
Best For
Multimodal (text, vision, audio)
Strong instruction following
Broad benchmark coverage
Fast API response times
Limitations
128K context smaller than some competitors
Proprietary — no local deployment
Premium pricing for high-volume use
Tags
VisionMultimodalCodingReasoningTool Use