GeniusRelay
Sign upConsole

OpenAI: GPT-4o (2024-11-20)

gpt-4o-2024-11-20

CompareAPIGet an API keyGet an API key

GPT-4o (2024-11-20) costs $3.25 per million input tokens and $13.00 per million output tokens, supports 128K context, and is available through the OpenAI-compatible API.

OpenAI's precusor to ChatGPT-4o. Great on English text and code, with significant improvements on text in non-English languages.

Modalities

Text + Image → Text

Input / output price

$3.25 / $13.00 per 1M

Context

128K · max output 16K

Capabilities

VisionTool calling

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$3.25
Output$13.00
Cached input$1.63

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.0202
Per day
$10.08
Per month (30 days)
$302.25

GPT-4o (2024-11-20): input $3.25/M · output $13/M · cached input $1.625/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4o-2024-11-20", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to gpt-4o-2024-11-20.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-2024-11-20",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is GPT-4o (2024-11-20) billed?
Input is $3.25 and output is $13.00 per million tokens; cached input is $1.63. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
128K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.
GPT-4o (2024-11-20) API pricing · GeniusRelay