We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
OpenAI: gpt-oss-120b
openai/gpt-oss-120bTry OpenAI: gpt-oss-120b now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
OpenAI: gpt-oss-120b at a glance
- Input price is 67% lower than the median of 434 Text models.
- Context window of 131,072 tokens, enough for long documents and multi-turn conversations.
- Supports tool (function) calling for agents and integrations.
- Supports structured JSON output with a schema.
- Supports reasoning effort control.
- A typical request (1,000 input / 500 output tokens) costs about $0.00158.
About OpenAI: gpt-oss-120b
OpenAI: gpt-oss-120b is an open-weight language model from OpenAI. It is a Mixture-of-Experts (MoE) model with 117B total parameters, of which 5.1B are activated per forward pass. It was released by the provider on 2025-08-05 and is designed for high-reasoning, agentic, and general-purpose production use cases.
The model works with text input and produces text output. It has a context window of 131072 tokens and a maximum output of 117964 tokens, so long inputs and long generations both fit comfortably within a single request. Its knowledge cutoff is 2024-06-30. As an MoE model it activates only a fraction of its parameters per forward pass, which is relevant if you care about how the model is served rather than only about its output.
Because it is built for reasoning and agentic work, the natural fits are tasks where the model has to think through a problem before answering: multi-step analysis, planning, and tool-driven workflows. The tool and structured output parameters make it usable as the reasoning core of an agent that calls functions or returns JSON. General-purpose text generation, summarization, and question answering over long documents also follow from the large context window and text-only interface.
You call it through api14's OpenAI-compatible API using the model id "openai/gpt-oss-120b". The supported request parameters are frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_a, top_k, top_logprobs and top_p. Reasoning behaviour is controlled through the reasoning, reasoning_effort and include_reasoning parameters, and tool use through tools and tool_choice. Sampling can be tuned with temperature, top_p, top_k, min_p, top_a, the penalty parameters and seed, while response_format and structured_outputs cover structured replies.
Two constraints are worth noting before you commit. Input and output are text only, so if your application needs to send or receive images or audio, this model is not the right fit. The knowledge cutoff of 2024-06-30 also means the model has no built-in awareness of anything after that date, so for questions about recent events you would need to supply the information in the prompt or through tools.
How to call the OpenAI: gpt-oss-120b API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "openai/gpt-oss-120b".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "openai/gpt-oss-120b",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_pSpecifications
- Context length
- 131,072
- Max output
- 65,536
- Input
- text
- Output
- text
- Knowledge cutoff
- 2024-06-30
Requests on api14 · last 7 days
OpenAI: gpt-oss-120b: frequently asked questions
- How much does the OpenAI: gpt-oss-120b API cost?
- OpenAI: gpt-oss-120b costs Input $0.52 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of OpenAI: gpt-oss-120b?
- OpenAI: gpt-oss-120b reads up to 131,072 tokens per request: prompt, history and documents together. It writes up to 65,536 output tokens per response.
- What can OpenAI: gpt-oss-120b do?
- OpenAI: gpt-oss-120b accepts text and returns text. It supports tool calling, structured JSON output, reasoning effort control.
- How do I call OpenAI: gpt-oss-120b from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "openai/gpt-oss-120b". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to OpenAI: gpt-oss-120b?
- Comparable Text models at a similar price: MiniMax: MiniMax M3.1 Flash, DeepSeek: DeepSeek V4.1 Flash 1017, LiquidAI: LFM2.5-24B-A2B. Each runs through the same API key, so switching is one string.
OpenAI: gpt-oss-120b community
New topicThis community has no topics yet. Open the first one about OpenAI: gpt-oss-120b.