OpenAI

gpt-4.1

$2 in · $8 out per million tokens · 1,000,000 tokens of context · first token in 551 ms

Get an API key

Price, limits and measured speed

Input price
$2 per million tokens
gateway.plungeai.com
Output price
$8 per million tokens
gateway.plungeai.com
OpenAI's list price, input
$2 per million tokens
OpenAI's list price, as our price feed records it
OpenAI's list price, output
$8 per million tokens
OpenAI's list price, as our price feed records it
Against the list price
At the list price
gateway.plungeai.com
Context window
1,000,000 tokens
gateway.plungeai.com
Tool calling
Yes
gateway.plungeai.com
Reads images
No
gateway.plungeai.com
Streams its answer
Yes
gateway.plungeai.com
Takes
text
gateway.plungeai.com
Request parameters
27 supported
gateway.plungeai.com
Served by
OpenAI
gateway.plungeai.com
Time to first token
551 ms
our probe of 22 November 2026 · measured by us
Output speed
296.5 tokens a second
our probe of 22 November 2026 · measured by us
Price of our test call
$0.00102
our probe of 22 November 2026, as the API stated it · measured by us
Input price rank
41st lowest of 55 chat models
the models on this site we could call · measured by us
Output price rank
36th lowest of 55
the models on this site we could call · measured by us
First-token rank
10th fastest of 55 measured
our probe of 22 November 2026 · measured by us
Output speed rank
9th fastest of 42 measured
our probe of 22 November 2026 · measured by us
Context rank
15th largest of 55
the models on this site we could call · measured by us

Call it

curl

curl https://api.plungeai.com/v1/chat/completions \
  -H "Authorization: Bearer $PLUNGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4.1",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

What it costs for three jobs

The same three jobs on every model page, so two models can be compared.

The cost of three reference workloads on openai/gpt-4.1
JobTokens inTokens outThrough One APIAt OpenAI's list price
A chat turn1,000300$0.0044$0.0044
An answer over retrieved documents8,000500$0.02$0.02
A summary of a long document100,0002,000$0.216$0.216

Models near it

Each against gpt-4.1: its input price and the time to its first token.

Models related to openai/gpt-4.1 by provider, price and context
ModelWhy it is hereInput price against itFirst token against itInput, $ per 1MOutput, $ per 1MContext, tokensFirst tokenTokens a second
openai/gpt-5.6-terraSame providerthe same+294 ms$2$121,000,000845 ms222.1
openai/gpt-6.1-solSame providerthe same+747 ms$2$101,050,0001,298 ms183.2
openai/o3Same providerthe same+1,499 ms$2$8200,0002,050 ms229.2
openai/gpt-6.1-terraCheaper, same abilities−50 %+583 ms$1$51,050,0001,134 ms94.8
google/gemini-3.8-flashCheaper, same abilities−59 %+2,269 ms$0.825$4.1251,048,5762,820 msnot measured
google/gemini-3.1-pro-previewLarger contextthe same+3,791 ms$2$121,048,5764,342 msnot measured

Request options

What openai/gpt-4.1 returns and the request parameters it accepts
SettingValue
Returnstext
Request parameterstemperature, top_p, max_tokens, max_completion_tokens, stop, tools, tool_choice, response_format, n, seed, presence_penalty, frequency_penalty, logprobs, top_logprobs, logit_bias, parallel_tool_calls, reasoning_effort, audio, functions, function_call, prompt_cache_key, safety_identifier, metadata, prediction, web_search_options, verbosity, modalities

In short

  • One API charges OpenAI's list price for gpt-4.1: $2 in and $8 out per million tokens.
  • By input price it is the 41st lowest of the 55 chat models we could call on 22 November 2026.
  • Its first token arrived after 551 ms in our test; the median of the 23 OpenAI models we called was 1,047 ms.
  • Its context window of 1,000,000 tokens holds about 2,000 pages of text at 500 tokens a page.

How this page is made

Prices, context sizes and abilities are read from One API's public price feed and its model endpoints each time this page is built. The time to the first token, the output speed and the price of a call are measured by us: 3 calls for each model through a One API key on 22 November 2026, entering at not recorded. A model that did not answer has no page. How we measure.

Data checked · Last changed

Get an API key