GeniusRelay
Sign upConsole

OpenAI: GPT 4.1

gpt-4.1

CompareAPIGet an API keyGet an API key

GPT 4.1 costs $2.60 per million input tokens and $10.40 per million output tokens, supports 1.05M context, and is available through the OpenAI-compatible API.

GPT 4.1 is the new flagship model from OpenAI. Huge context window (1 mln tokens), outperforms GPT-4o and GPT 4.5 across coding and does very well at understanding large contexts.

Modalities

Text + Image → Text

Input / output price

$2.60 / $10.40 per 1M

Context

1.05M · max output 33K

Capabilities

VisionTool callingLong context

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$2.60
Output$10.40
Cached input$0.650

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.0161
Per day
$8.06
Per month (30 days)
$241.80

GPT 4.1: input $2.6/M · output $10.4/M · cached input $0.65/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-4.1", "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-4.1.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "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 4.1 billed?
Input is $2.60 and output is $10.40 per million tokens; cached input is $0.650. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
1.05M 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 4.1 API pricing · GeniusRelay