TypingMind×
GroqHow to use GPT OSS 120B with your Groq API key on TypingMind
Learn how to access and use GPT OSS 120B with your Groq API key through TypingMind. Get started with this AI model in minutes.
Open GPT reasoning model for self-hosted agents and controllable deployments
Groq is the world's fastest AI inference platform powered by the proprietary LPU™ (Language Processing Unit) Inference Engine, purpose-built hardware designed specifically for running large language models at exceptional speed and low cost.
The LPU architecture delivers 300-500 tokens per second with up to 18x faster processing than traditional GPUs through tensor streaming technology optimized for sequential computation and low-latency inference. GroqCloud provides API access to leading open-source models (Llama, Mixtral, Gemma) with Tokens-as-a-Service pricing, enabling developers to build production-ready AI applications with ultra-low latency and high throughput.
Key features include deterministic performance, reduced memory bottlenecks, energy-efficient processing, real-time inference capabilities, and scalable cloud deployment with straightforward API integration.
See the official Groq documentation for more details.
GPT OSS 120B Overview
| Model Name | GPT OSS 120B |
| Provider | Groq |
| Model ID | openai/gpt-oss-120b |
| Model Logo | Get the logo URL |
| Release Date | Aug 5, 2025 |
| Last Updated | Oct 21, 2025 |
| Context Window | 131,072 tokens |
| Max Output | 65,536 tokens |
| Pricing /1M tokens | $0.15 input $0.60 output $0.075 cache read |
| Input Modalities | text |
| Output Modalities | text |
| Capabilities | ReasoningTool CallingStructured OutputTemperature ControlOpen Weights |
Complete Setup Guide
Get Your Groq API Key
First, you'll need to obtain an API key from Groq. This key allows you to access their AI models directly and pay only for what you use.
- Visit Groq's API console
- Sign up or log in to your account
- Navigate to the API keys section
- Generate a new API key (copy it immediately as some providers only show it once)
- Save your API key in a secure password manager or encrypted note
Sometimes, this provider will require you to add a payment method to your account before you can use your API key to chat with AI. So, to avoid any hiccups, make sure you've got a payment method set up and ready to go!
Important: Keep your API key secure and never share it publicly. Store it safely as you'll need it to connect with TypingMind.
Configure TypingMind with Groq API Key
Option 1: Use the built-in Groq provider (recommended)
The quickest way. TypingMind already has Groq set up, so you only need to add your API key.
- Open TypingMind and click "Models" in the left sidebar.
- Search for Groq.
- Click the settings (gear) button next to Groq.
- Paste your API key and save.
Option 2: Add the model manually
If you can't find the provider or model ID in the official list, you can add the model manually:
Open the Models page
Open TypingMind, click "Models" in the left sidebar, then click "Add custom model" in the top right corner.
Enter the model details
Keep "Create Manually" selected and fill in the model details:
Name:GPT OSS 120B via Groq(or your preferred name)Model ID:openai/gpt-oss-120bfor example (check Groq model list)Context Length: Enter the model's context window (e.g., 131072 for openai/gpt-oss-120b)
Set up authentication
In the "Authentication" tab, set the connection details:
API Type:OpenAI Chat Completions APIEndpoint URL:https://api.groq.com/openai/v1/chat/completionsAuthentication Type:API Key via HTTP HeaderHeader Key:AuthorizationHeader Value:Bearer <GROQ_API_KEY>
Add pricing (optional)
Open the "Pricing" tab and enter the model's input, output, and cache prices per 1M tokens so TypingMind can estimate your usage costs.
Check the capabilities
In the "Capabilities" tab, keep "Auto check capabilities on save" on so TypingMind detects supported features like plugins, image input, and thinking, or enable them manually.
Test and save
Click "Test & Save" to verify the connection and add the model.
Start chatting with GPT OSS 120B
Now you can start chatting with GPT OSS 120B through TypingMind:
- Select GPT OSS 120B from the model dropdown menu
- Start typing your message in the chat input
- Enjoy faster responses and better features than the official interface
- Switch between different AI models as needed
💡 Pro tips for better results:
- Use specific, detailed prompts for better responses (How to use Prompt Library)
- Create AI agents with custom instructions for repeated tasks (How to create AI Agents)
- Use plugins to extend GPT OSS 120B with web search, code execution, and more (How to use plugins)
Why TypingMind + Groq?
Chat with GPT OSS 120B and 200+ other models in one workspace, using your own Groq API key.
Best-in-class UI
TypingMind's interface is far superior to standard chat UIs.
Model flexibility
Switch between GPT OSS 120B and 200+ models instantly.
Cost control
Pay only for what you use through Groq.
One-time purchase
Buy TypingMind once, use forever with any Groq model.
Data privacy
Your conversations are stored locally by default, not on external servers.
Plugins, MCP, Skills & AI agents
Extend GPT OSS 120B with web search, image generation, and custom AI agents.
Frequently Asked Questions
Do I need a subscription to use GPT OSS 120B?
No. With your own Groq API key, you pay only for what you use, with no monthly subscription. TypingMind is also a one-time purchase, not a subscription.
How much does it cost to use GPT OSS 120B?
GPT OSS 120B costs $0.15/1M input tokens and $0.60/1M output tokens via Groq. A typical conversation costs around $0.01-0.10, depending on length.
Can I use other models besides GPT OSS 120B?
Yes. Any model your Groq API key can access works in TypingMind, and you can switch between it and models from other providers in the same chat.
Is my data private when using GPT OSS 120B with TypingMind?
TypingMind stores your conversations locally (in your browser on the web version, on your device in the desktop app). Your messages are sent to Groq with your API key, so check Groq's data policy for how it handles API requests.
