OpenAIFeb 28, 2026
GPT-4o
OpenAI’s multimodal model with vision capabilities, strong reasoning, and broad knowledge. Popular for its balanced performance across tasks. Version: 2024-11-20.
$2.50/$10.00
per 1M in / out
128K
context window
16K
max output
Time to first token—
Output speed—
Uptime—
Last 24 hours of Venice traffic.How it’s measured
Capabilities
What the model takes in, returns and supports through the API.
InTextImage
OutText
Streaming
Function callingstream: truetoolsStructured outputsresponse_formatVisionUp to 10 imagesWeb search
Prompt cachingReads at $1.25enable_web_searchLog probabilities
logprobsNot supportedreasoning, video input, audio input and X search
Benchmarks
GPQA Diamond
50.0%126th of 139 · 90 score higher for less, including GPT-6.2 Sol, GPT-6.2 Sol Pro and Gemini 3.8 Flash
Specs
- Model ID
openai-gpt-4o-2024-11-20- Endpoint
POST /api/v1/chat/completions- Context window
- 128,000 tokens
- Max output
- 16,384 tokens
- Reasoning
- None
- Precision
- Set by the provider
- Privacy
- Anonymized
- Weights
- Closed
- Added
- Feb 28, 2026
Compare
| Model | Input | Output |
|---|---|---|
| GPT-4o | $2.50 | $10.00 |
| Qwen 3.7 Max | $2.70 | $8.05 |
| Aion 3.0 | $3.75 | $7.50 |
| Claude Sonnet 5 | $2.00 | $10.00 |
| Gemini 3.1 Pro Preview | $2.50 | $15.00 |
Pricing
Billed per token in USD. Reasoning tokens bill as output.
Input$2.50per 1M tokens
Cached input$1.2550% off input
Output$10.00per 1M tokens
Estimate a workload
$0.01per request
$100for 10,000 requests
Blended price against similar models
Quickstart
OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.
curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai-gpt-4o-2024-11-20",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
}'Base URL
https://api.venice.ai/api/v1Parameters
| Parameter | Values |
|---|---|
model | openai-gpt-4o-2024-11-20 |
messages | text · image_url |
max_completion_tokens | Up to 16,384 |
tools | Function definitions |
response_format | { type: |
stream | true | false |
venice_parameters.enable_web_search | auto | on | off |
logprobs | true | false |