Ann NgAnn Ng
5 min read

How to use Llama 3.1 70B Turbo from DeepInfra with API Key on TypingMind

Learn how to access and use Llama 3.1 70B Turbo with your DeepInfra API key through TypingMind. Get started with this powerful AI model in minutes.

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.

Official Documentation: https://deepinfra.com/models

Llama 3.1 70B Turbo Overview

Model NameLlama 3.1 70B Turbo
ProviderDeepInfra
Model IDmeta-llama/Llama-3.1-70B-Instruct-Turbo
Release DateJul 23, 2024
Last UpdatedJul 23, 2024
Context Window131,072 tokens
Max Output16,384 tokens
Pricing /1M tokens$0.4 input
$0.4 output
Input Modalitiestext
Output Modalitiestext
Capabilities
Tool CallingOpen Weights

Complete Setup Guide

1

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.

  1. Visit DeepInfra's API console
  2. Sign up or log in to your account
  3. Navigate to the API keys section
  4. Generate a new API key (copy it immediately as some providers only show it once)
  5. Save your API key in a secure password manager or encrypted note

⚠️ Important: Keep your API key secure and never share it publicly. Store it safely as you'll need it to connect with TypingMind.

2

Configure TypingMind with DeepInfra API Key

  1. Open TypingMind in your browser
  2. Click the "Settings" icon (gear symbol)
  3. Navigate to "Models" section
  4. Click "Add Custom Model"
  5. Fill in the model information:
    Name: meta-llama/Llama-3.1-70B-Instruct-Turbo via DeepInfra (or your preferred name)
    Endpoint: https://api.deepinfra.com/v1/chat/completions
    Model ID: meta-llama/Llama-3.1-70B-Instruct-Turbo
    Context Length: Enter the model's context window (e.g., 131072 for meta-llama/Llama-3.1-70B-Instruct-Turbo)
    DeepInfra Endpoint URL input fieldmeta-llama/Llama-3.1-70B-Instruct-Turbohttps://api.deepinfra.com/v1/chat/completionsmeta-llama/Llama-3.1-70B-Instruct-Turbo via DeepInfrahttps://www.typingmind.com/model-logo.webp131072
  6. Add custom headers by clicking "Add Custom Headers" in the Advanced Settings section:
    Authorization: Bearer <DEEPINFRA_API_KEY>:
    X-Title: typingmind.com
    HTTP-Referer: https://www.typingmind.com
  7. Enable "Support Plugins (via OpenAI Functions)" if the model supports the "functions" or "tool_calls" parameter, or enable "Support OpenAI Vision" if the model supports vision.
  8. Click "Test" to verify the configuration
  9. If you see "Nice, the endpoint is working!", click "Add Model"
3

Start chatting with Llama 3.1 70B Turbo

Now you can start chatting with Llama 3.1 70B Turbo through TypingMind:

  • Select Llama 3.1 70B Turbo 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
The best frontend AI chat for meta-llama/Llama-3.1-70B-Instruct-Turbo via OpenRouter API KeyThe best frontend AI chat for meta-llama/Llama-3.1-70B-Instruct-Turbo via OpenRouter API Keymeta-llama/Llama-3.1-70B-Instruct-TurboThe best frontend AI chat for meta-llama/Llama-3.1-70B-Instruct-Turbo via OpenRouter API Key

💡 Pro tips for better results:

Frequently Asked Questions

Do I need a subscription to use Llama 3.1 70B Turbo?

No! With DeepInfra API, you pay only for what you use with no monthly subscription. Add credits to your DeepInfra account and pay as you go. TypingMind is also a one-time purchase, not a subscription.

How much will it cost to use Llama 3.1 70B Turbo?

Llama 3.1 70B Turbo costs $0.4/1M input tokens and $0.4/1M output tokens. A typical conversation might cost $0.01-0.10 depending on length.

Can I use other models besides Llama 3.1 70B Turbo?

Yes! With DeepInfra API + TypingMind, you can access all DeepInfra models. Switch between them instantly in TypingMind.

Is my data private and secure?

Yes! TypingMind stores conversations locally (web version in browser, desktop version on your device). DeepInfra handles API calls securely. Check DeepInfra's data policy for specifics.

Can I use Llama 3.1 70B Turbo for commercial projects?

Yes! Check DeepInfra's terms of service for specific commercial use policies. TypingMind supports commercial use.