OpenAI

gpt-4o

$2.5 in · $10 out per million tokens · 128,000 tokens of context · first token in 506 ms

Get an API key

Price, limits and measured speed

Input price
$2.5 per million tokens
gateway.plungeai.com
Output price
$10 per million tokens
gateway.plungeai.com
OpenAI's list price, input
$2.5 per million tokens
OpenAI's list price, as our price feed records it
OpenAI's list price, output
$10 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
128,000 tokens
gateway.plungeai.com
Tool calling
Yes
gateway.plungeai.com
Reads images
Yes
gateway.plungeai.com
Streams its answer
Yes
gateway.plungeai.com
Takes
text, image
gateway.plungeai.com
Request parameters
27 supported
gateway.plungeai.com
Served by
OpenAI
gateway.plungeai.com
Time to first token
506 ms
our probe of 22 November 2026 · measured by us
Output speed
224.5 tokens a second
our probe of 22 November 2026 · measured by us
Price of our test call
$0.000195
our probe of 22 November 2026, as the API stated it · measured by us
Input price rank
48th lowest of 55 chat models
the models on this site we could call · measured by us
Output price rank
39th lowest of 55
the models on this site we could call · measured by us
First-token rank
8th fastest of 55 measured
our probe of 22 November 2026 · measured by us
Output speed rank
17th fastest of 42 measured
our probe of 22 November 2026 · measured by us
Context rank
51st 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-4o",
    "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-4o
JobTokens inTokens outThrough One APIAt OpenAI's list price
A chat turn1,000300$0.0055$0.0055
An answer over retrieved documents8,000500$0.025$0.025
A summary of a long document100,0002,000$0.27$0.27

Models near it

Each against gpt-4o: its input price and the time to its first token.

Models related to openai/gpt-4o 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-5.4Same providerthe same+251 ms$2.5$15400,000757 ms175.6
openai/gpt-4.1Same provider−20 %+45 ms$2$81,000,000551 ms296.5
openai/gpt-5.6-terraSame provider−20 %+339 ms$2$121,000,000845 ms222.1
google/gemini-3.5-flashCheaper, same abilities−40 %+1,563 ms$1.5$91,000,0002,069 msnot measured
google/gemini-2.5-proCheaper, same abilities−50 %+1,722 ms$1.25$102,000,0002,228 msnot measured
anthropic/claude-sonnet-5.5Larger context−20 %+1,039 ms$2$101,000,0001,545 ms186.6

Request options

What openai/gpt-4o 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-4o: $2.5 in and $10 out per million tokens.
  • By input price it is the 48th lowest of the 55 chat models we could call on 22 November 2026.
  • Its first token arrived after 506 ms in our test; the median of the 23 OpenAI models we called was 1,047 ms.
  • Its context window of 128,000 tokens holds about 256 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