GPT-4o

openai/gpt-4o

GPT-4o ("o" for "omni") is OpenAI's versatile, high-intelligence GPT model released in May 2024, accepting text and image input and producing text output, including Structured Outputs. OpenAI describes it as fast and flexible, suited to general-purpose chat, image understanding, function calling and non-English language tasks. This entry tracks OpenAI's default GPT-4o alias; use one of the dated GPT-4o snapshots when a workload needs fixed behavior.

Input price
$2.50USD / 1M tokens
Output price
$10.00USD / 1M tokens
Cache read
$1.25USD / 1M tokens
Context window
128K
Max output
16.4K

Specifications

CapabilitiesChatVisionStructured outputFunction calling
Input
Text, image
Output
Text
Available

Questions

FAQ

How do I call OpenAI GPT-4o through SandBase?

Create a SandBase API key, then send requests with the model ID "openai/gpt-4o" to Responses API (/v1/responses) or Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

How much does OpenAI GPT-4o cost?

$2.50 per 1M input tokens and $10 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

What is the context window of OpenAI GPT-4o?

128K tokens of context, with up to 16.4K output tokens per response.

Which features does OpenAI GPT-4o support?

OpenAI GPT-4o supports vision (image input), function calling, structured output. See Specifications above for the full list.

Do I need a separate OpenAI account?

No. One SandBase API key and balance gives you access to OpenAI GPT-4o and the other models in the catalog; you do not need to sign up with OpenAI separately.