GPT-4o

We haven't added a description for this model yet. You can still review capabilities and run live tests below.

Input: textOutput: text

Streaming

Function calling

System messages

Context length

128,000 tokens

Max output tokens

16,400 tokens

Provider streaming support: Enabled

Pricing information not available for this model.

Try GPT-4o

Run live prompts using your own API key. We’ll display any token usage returned by the provider so you can estimate credits before integrating.

Send a quick request to GPT-4o.

API Key

The key is only used client-side to call your authenticated API.

System Message (optional)

User Message

Use streaming response

Temperature

Max Tokens

POST /api/v1/chat/completions

Authorization: Bearer ••••

Content-Type: application/json

// Submit the form to view payload

Inspect status, headers, timing, and usage metadata

Trigger a request to inspect response metadata.

Raw Response

// Response body will appear here

Run a request to view prompt, completion, and total token usage.