About DeepInfra

DeepInfra is a cloud inference platform providing fast and cost-effective access to a wide range of open-source AI models including Llama, Mistral, DeepSeek, and more through an OpenAI-compatible API.

Key features include serverless inference with pay-per-token pricing, support for text generation, embeddings, and image models, low-latency responses powered by optimized GPU infrastructure, and easy integration with any OpenAI-compatible client or SDK.

Step by step guide to use DeepInfra API Key to chat with AI

I. Get Your DeepInfra API Key

First, you'll need to obtain an API key from DeepInfra. This key allows you to access their AI models directly and pay only for what you use.

Visit DeepInfra'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.

II. Connect Your DeepInfra API Key on TypingMind

Once you have your DeepInfra API key, connecting it to TypingMind to chat with AI is straightforward:

Option 1: Use the built-in Deepinfra provider (recommended)

The quickest way. TypingMind already has Deepinfra set up, so you only need to add your API key.

Open TypingMind and click "Models" in the left sidebar.
Search for Deepinfra.
Click the settings (gear) button next to Deepinfra.
Paste your API key and save.

Built-in providers with settings buttons on the TypingMind Models page

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: openai/gpt-oss-120b via DeepInfra (or your preferred name)
Model ID: openai/gpt-oss-120b for example (check DeepInfra 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 API
Endpoint URL: https://api.deepinfra.com/v1/chat/completions
Authentication Type: API Key via HTTP Header
Header Key: Authorization
Header Value: Bearer <DEEPINFRA_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.

III. Start Chatting with DeepInfra models

Now you can start chatting with DeepInfra models through TypingMind:

Select DeepInfra models 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

Chat with DeepInfra models on TypingMind

💡 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 DeepInfra models with web search, code execution, and more (How to use plugins)
Upload documents and images directly to chat for AI analysis and discussion (Chat with documents)

IV. Monitor Your AI Usage and Costs

One of the biggest advantages of using API keys with TypingMind is cost transparency and control. Unlike fixed subscriptions, you pay only for what you actually use. Visit your DeepInfra usage dashboard to monitor your API usage and set spending limits.

💡 Cost-saving tips:

Use less expensive models for simple tasks
Keep prompts concise but specific to reduce token usage
Use TypingMind's prompt caching to reduce repeat costs (How to enable prompt caching)
Using RAG (retrieval-augmented generation) for large documents to reduce repeat costs (How to use RAG)

Why TypingMind + DeepInfra?

Chat with DeepInfra models and 200+ other models in one workspace, using your own DeepInfra API key.

Best-in-class UI

TypingMind's interface is far superior to standard chat UIs.

Model flexibility

Switch between DeepInfra models and 200+ models instantly.

Cost control

Pay only for what you use through DeepInfra.

One-time purchase

Buy TypingMind once, use forever with any DeepInfra model.

Data privacy

Your conversations are stored locally by default, not on external servers.

Plugins, MCP, Skills & AI agents

Extend DeepInfra models with web search, image generation, and custom AI agents.

Try TypingMind for free

Frequently Asked Questions

Do I need a subscription to use DeepInfra with TypingMind?

No. With your own DeepInfra 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 the DeepInfra API cost?

DeepInfra charges per token, and prices vary by model. For example, openai/gpt-oss-120b costs $0.037/1M input tokens and $0.17/1M output tokens. A typical conversation costs around $0.01-0.10, depending on the model and length.

Which DeepInfra models can I use in TypingMind?

Any model your DeepInfra API key can access. You can switch between DeepInfra models and models from other providers in the same TypingMind chat.

Is my data private when using DeepInfra 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 DeepInfra with your API key, so check DeepInfra's data policy for how it handles API requests.