How much does gpt-oss-120b (free) cost via API?

It's free: $0 per 1M input tokens and $0 per 1M output tokens from the provider. OpenKey applies its flat 3% fee to provider pricing ($0 x 1.03 = $0), so there's no cost either way. It's one of 25 free models available on OpenKey out of 329 total.

What is gpt-oss-120b's context window?

The context window is 131,072 tokens, covering roughly 90,000-100,000 words of input and output combined. That places it above 23% of models in the OpenKey catalog by context length. Max completion length matches the full context window at 131,072 tokens.

Is gpt-oss-120b (free) actually free to use?

Yes — provider pricing is $0.00 per 1M tokens for both input and output, and OpenKey doesn't add its 3% fee on top of a zero base price. It's one of 25 free models on the platform.

Does gpt-oss-120b support tool calling?

Yes. It supports 'tools' and 'tool_choice' as parameters, along with structured controls like seed, temperature, top_p, top_k, and reasoning effort. It does not support image or audio input — this is a text-in, text-out model only.

Can I turn off reasoning on gpt-oss-120b?

No. Reasoning is mandatory on this model — you can only choose how much: low, medium, or high effort, with medium as the default. This differs from models where reasoning is an optional toggle; here every request pays some reasoning cost.

gpt-oss-120b (free)

openaigpt-oss-120b:free

Free

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

Try in playground Hugging Face ↗

Modalities: text → text
In / out per 1M: Free / Free
Context: 131K tokens
Added: Aug 5, 2025

Max output: 131K tokens
Tokenizer: GPT
Knowledge cutoff: Jun 30, 2024
Reasoning: always on

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokens	Provider	+ 3% fee	You pay
Input	Free	—	Free
Output	Free	—	Free

Providers

No provider breakdown is published for gpt-oss-120b (free) in the current catalog snapshot (Jul 28, 2026). Browse all providers

Benchmarks

Artificial Analysis

Agentic index: 13.2
Coding index: 30.4
Intelligence index: 23.8

Design Arena

Category	Elo	Win rate	Rank
3D models	978	29.4%	#90
Code models	1013	33.4%	#96
Data viz models	1044	45.1%	#86
Game dev models	1059	40.6%	#84
UI components models	980	35.5%	#91
Websites models	1011	32.5%	#99

Head-to-head preference voting. How we filter and rank

Supported parameters

include_reasoning
max_tokens
min_p
reasoning
seed
stop
temperature
tool_choice
tools
top_a
top_k
top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model openai/gpt-oss-120b:free.

curl Python TypeScript

curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer ***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-oss-120b:free",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="openai/gpt-oss-120b:free",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "openai/gpt-oss-120b:free",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

About gpt-oss-120b (free)

gpt-oss-120b is OpenAI's open-weight Mixture-of-Experts model: 117B total parameters, but only 5.1B activate per forward pass, which is what makes it cheap to run at scale despite the large parameter count. Reasoning is mandatory here, not optional — every request runs through a low/medium/high effort setting, defaulting to medium. On Artificial Analysis benchmarks it scores 23.8 on the intelligence index and 30.4 on coding, with a 131,072-token context window and a June 30, 2024 knowledge cutoff. Text in, text out — no vision or audio.

This is a free model on OpenKey: $0 input and $0 output per 1M tokens, so the 3% fee ($0 x 1.03 = $0) doesn't change anything. Its 131,072-token context window beats 23% of the catalog. Unlike most OpenAI models, reasoning can't be turned off — you pick an effort level (low, medium, high) but you can't skip the reasoning step. Its agentic index (13.2) trails its coding score (30.4), so it's stronger at writing code than at multi-step autonomous tasks.

Questions

How much does gpt-oss-120b (free) cost via API?: It's free: $0 per 1M input tokens and $0 per 1M output tokens from the provider. OpenKey applies its flat 3% fee to provider pricing ($0 x 1.03 = $0), so there's no cost either way. It's one of 25 free models available on OpenKey out of 329 total.
What is gpt-oss-120b's context window?: The context window is 131,072 tokens, covering roughly 90,000-100,000 words of input and output combined. That places it above 23% of models in the OpenKey catalog by context length. Max completion length matches the full context window at 131,072 tokens.
Is gpt-oss-120b (free) actually free to use?: Yes — provider pricing is $0.00 per 1M tokens for both input and output, and OpenKey doesn't add its 3% fee on top of a zero base price. It's one of 25 free models on the platform.
Does gpt-oss-120b support tool calling?: Yes. It supports 'tools' and 'tool_choice' as parameters, along with structured controls like seed, temperature, top_p, top_k, and reasoning effort. It does not support image or audio input — this is a text-in, text-out model only.
Can I turn off reasoning on gpt-oss-120b?: No. Reasoning is mandatory on this model — you can only choose how much: low, medium, or high effort, with medium as the default. This differs from models where reasoning is an optional toggle; here every request pays some reasoning cost.

More from OpenAI

All OpenAI models →

OpenAI

GPT Chat Latest

GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...

ctx 400K in $5.15 out $30.90

OpenAI

OpenAI GPT Latest

This model always redirects to the latest model in the OpenAI GPT family.

ctx 1.1M in $5.15 out $30.90

OpenAI

OpenAI GPT Mini Latest

This model always redirects to the latest model in the OpenAI GPT Mini family.

ctx 400K in $0.772 out $4.63

OpenAI

GPT-5.5

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...

ctx 1.1M in $5.15 out $30.90