gpt-oss-120b

Name: OpenAI gpt-oss-120b
Price: 0.039 USD
Availability: InStock
Author: OpenAI

openai/gpt-oss-120b

gpt-oss-120b is OpenAI's largest open-weight reasoning model, released in August 2025 under the Apache 2.0 license: a 117B-parameter mixture-of-experts model with 5.1B active parameters that fits on a single 80GB GPU. OpenAI positions it for production, general-purpose and high-reasoning use, with adjustable low, medium or high reasoning, full chain-of-thought access, and native function calling, browsing, Python execution and structured outputs. It is text-only and can be self-hosted or fine-tuned.

Use in agent Get API key

Input price: $0.04USD / 1M tokens
Output price: $0.18USD / 1M tokens
Context window: 131.1K
Max output: 131.1K

Production route

Try the model

Playground

Open playground

Input⌘ / Ctrl + Enter

Try a prompt

Prompt

131.1K context131.1K max output

Input$0.04/MOutput$0.18/M

OutputReady

Your response will appear here

Choose an example or write a prompt, then click Run.

Model card

Specifications

Pricing

Input: $0.04 / 1M tokens
Output: $0.18 / 1M tokens

Context & modalities

Context window: 131,072 tokens
Max output: 131,072 tokens
Input: Text
Output: Text

Capabilities

Chat: Supported
Vision: Not supported
Reasoning: Supported
Structured output: Supported
Function calling: Supported
Audio input: Not supported

Access

Provider: OpenAI
Model ID: openai/gpt-oss-120b
Execution: sync
Base URL: https://api.sandbase.ai
API: Responses API
Endpoint: /v1/responses
API: Chat Completions API
Endpoint: /v1/chat/completions

Start building

Send your first request

Choose either supported API with unified authentication and usage tracking.

Production API

Responses API endpoint

https://api.sandbase.ai/v1/responses

Model ID

openai/gpt-oss-120b

# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/responses" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "openai/gpt-oss-120b",
  "input": "Hello",
  "max_output_tokens": 2048
}
SANDBASE_JSON
)
printf '%s\n' "$result"

Choose your model

Compare models

All language models

Model	Context	Input / 1M	Output / 1M	Released
gpt-oss-120bThis model `OpenAI`	128K	$0.04	$0.18	Aug 5, 2025
GPT-6.1 Terra Pro `OpenAI`	1.1M	$1.00	$5.00	Oct 26, 2026
GPT-6.1 Terra `OpenAI`	1.1M	$1.00	$5.00	Oct 26, 2026
GPT-6.1 Sol Pro `OpenAI`	1.1M	$2.00	$10.00	Sep 29, 2026
GPT-6.1 Sol `OpenAI`	1.1M	$2.00	$10.00	Sep 29, 2026
GPT-6 Luna Pro `OpenAI`	1.1M	$0.10	$0.50	Sep 22, 2026

Questions

FAQ

How do I call OpenAI gpt-oss-120b through SandBase?

Create a SandBase API key, then send requests with the model ID "openai/gpt-oss-120b" to Responses API (/v1/responses) or Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

How much does OpenAI gpt-oss-120b cost?

$0.04 per 1M input tokens and $0.18 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

What is the context window of OpenAI gpt-oss-120b?

131.1K tokens of context, with up to 131.1K output tokens per response.

Which features does OpenAI gpt-oss-120b support?

OpenAI gpt-oss-120b supports reasoning, function calling, structured output. See Specifications above for the full list.

Do I need a separate OpenAI account?

No. One SandBase API key and balance gives you access to OpenAI gpt-oss-120b and the other models in the catalog; you do not need to sign up with OpenAI separately.