OpenAI

gpt-oss-120b

$0.0463 in · $0.2125 out per million tokens · 131,072 tokens of context · first token in 1,060 ms

Get an API key

Price, limits and measured speed

Input price
$0.0463 per million tokens
gateway.plungeai.com
Output price
$0.2125 per million tokens
gateway.plungeai.com
OpenAI's list price, input
$0.15 per million tokens
console.groq.com
OpenAI's list price, output
$0.6 per million tokens
console.groq.com
Against the list price
65 % below the list price
gateway.plungeai.com
Context window
131,072 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
31 supported
gateway.plungeai.com
Served by
OpenAI
gateway.plungeai.com
Time to first token
1,060 ms
our probe of 22 November 2026 · measured by us
Output speed
11.2 tokens a second
our probe of 22 November 2026 · measured by us
Price of our test call
$0.000038
our probe of 22 November 2026, as the API stated it · measured by us
Input price rank
2nd lowest of 55 chat models
the models on this site we could call · measured by us
Output price rank
2nd lowest of 55
the models on this site we could call · measured by us
First-token rank
29th fastest of 55 measured
our probe of 22 November 2026 · measured by us
Output speed rank
39th fastest of 42 measured
our probe of 22 November 2026 · measured by us
Context rank
40th 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-oss-120b",
    "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-oss-120b
JobTokens inTokens outThrough One APIAt OpenAI's list price
A chat turn1,000300$0.00011$0.00033
An answer over retrieved documents8,000500$0.000477$0.0015
A summary of a long document100,0002,000$0.00506$0.0162

Models near it

Each against gpt-oss-120b: its input price and the time to its first token.

Models related to openai/gpt-oss-120b 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-nanoSame provider+8 %+1,652 ms$0.05$0.4400,0002,712 ms235.4
openai/gpt-6-lunaSame provider+116 %−65 ms$0.1$0.51,050,000995 ms179.1
openai/gpt-4o-miniSame provider+224 %−233 ms$0.15$0.6128,000827 ms72.1
deepinfra/openai/gpt-oss-120bCheaper, same abilities−20 %+132 ms$0.037$0.17131,0721,192 ms11.1
google/gemma-4-26b-a4b-itLarger context+46 %−78 ms$0.0675$0.225262,144982 msnot measured

Request options

What openai/gpt-oss-120b 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, top_k, min_p, top_a, repetition_penalty

What changed

Every change

In short

  • One API posts gpt-oss-120b at 65 % below OpenAI's list price: $0.0463 in and $0.2125 out per million tokens, against $0.15 and $0.6.
  • By input price it is the 2nd lowest of the 55 chat models we could call on 22 November 2026.
  • Its first token arrived after 1,060 ms in our test; the median of the 23 OpenAI models we called was 1,047 ms.
  • Its context window of 131,072 tokens holds about 262 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