OpenAI

gpt-5.4-nano

$0.2 in · $1.25 out per million tokens · 400,000 tokens of context · first token in 451 ms

Get an API key

Price, limits and measured speed

Input price
$0.2 per million tokens
gateway.plungeai.com
Output price
$1.25 per million tokens
gateway.plungeai.com
OpenAI's list price, input
$0.2 per million tokens
OpenAI's list price, as our price feed records it
OpenAI's list price, output
$1.25 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
400,000 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
451 ms
our probe of 22 November 2026 · measured by us
Output speed
159.3 tokens a second
our probe of 22 November 2026 · measured by us
Price of our test call
$0.000159
our probe of 22 November 2026, as the API stated it · measured by us
Input price rank
13th lowest of 55 chat models
the models on this site we could call · measured by us
Output price rank
18th lowest of 55
the models on this site we could call · measured by us
First-token rank
5th fastest of 55 measured
our probe of 22 November 2026 · measured by us
Output speed rank
29th fastest of 42 measured
our probe of 22 November 2026 · measured by us
Context rank
28th 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-5.4-nano",
    "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-5.4-nano
JobTokens inTokens outThrough One APIAt OpenAI's list price
A chat turn1,000300$0.000575$0.000575
An answer over retrieved documents8,000500$0.00222$0.00222
A summary of a long document100,0002,000$0.0225$0.0225

Models near it

Each against gpt-5.4-nano: its input price and the time to its first token.

Models related to openai/gpt-5.4-nano 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-lunaSame providerthe same+346 ms$0.2$1.21,000,000797 ms220
openai/gpt-4o-miniSame provider−25 %+376 ms$0.15$0.6128,000827 ms72.1
openai/gpt-5-miniSame provider+25 %+3,713 ms$0.25$2400,0004,164 ms124.6
anthropic/claude-haiku-5-5Cheaper, same abilities−50 %+562 ms$0.1$0.51,000,0001,013 ms749.2
google/gemini-2.5-flash-liteCheaper, same abilities−50 %+80 ms$0.1$0.41,048,576531 ms90.6
deepinfra/deepseek-ai/DeepSeek-V4.1-FlashLarger contextthe same+38 ms$0.2$0.61,048,576489 ms202.3

Request options

What openai/gpt-5.4-nano 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

What changed

  • gpt-5.4-nano A summary of a long document: $0.022 → $0.0225

Every change

In short

  • One API charges OpenAI's list price for gpt-5.4-nano: $0.2 in and $1.25 out per million tokens.
  • By input price it is the 13th lowest of the 55 chat models we could call on 22 November 2026.
  • Its first token arrived after 451 ms in our test; the median of the 23 OpenAI models we called was 1,047 ms.
  • Its context window of 400,000 tokens holds about 800 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