How to use Muse Spark Open with your Together AI API key on TypingMind

Learn how to access and use Muse Spark Open with your Together AI API key through TypingMind. Get started with this AI model in minutes.

Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.

Together AI is an AI cloud for running open-source models. Its serverless inference API gives pay-per-token access to models like Llama, DeepSeek, Qwen, GLM, Kimi, MiniMax, and gpt-oss through an OpenAI-compatible endpoint.

Beyond serverless inference, Together AI offers dedicated endpoints, fine-tuning, batch inference, and GPU clusters for teams that need more control over performance and cost.

See the official Together AI documentation for more details.

Muse Spark Open Overview

Model NameMuse Spark Open
ProviderTogether AI
Model IDmeta-models/Muse-Spark-Open-816B-A42B
Model LogoGet the logo URL
Release DateOct 15, 2026
Last UpdatedOct 15, 2026
Knowledge Cutoff2026-01-04
Context Window1,048,576 tokens
Max Output131,072 tokens
Pricing /1M tokens$1.25 input
$4.25 output
$0.15 cache read
Input Modalitiestext, image, video
Output Modalitiestext
Capabilities
File UploadReasoningTool CallingStructured OutputTemperature ControlOpen Weights

Complete Setup Guide

I

Get Your Together AI API Key

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

  1. Visit Together AI'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
Together AI API keys page

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

Configure TypingMind with Together AI API Key

  1. Open the Models page

    Open TypingMind, click "Models" in the left sidebar, then click "Add custom model" in the top right corner.

    TypingMind Models page with the Add custom model button
  2. Enter the model details

    Keep "Create Manually" selected and fill in the model details:

    Name: Muse Spark Open via Together AI (or your preferred name)
    Model ID: meta-models/Muse-Spark-Open-816B-A42B for example (check Together AI model list)
    Context Length: Enter the model's context window (e.g., 1048576 for meta-models/Muse-Spark-Open-816B-A42B)
    Add Custom Model dialog in TypingMind filled in for meta-models/Muse-Spark-Open-816B-A42B
  3. Set up authentication

    In the "Authentication" tab, set the connection details:

    API Type: OpenAI Chat Completions API
    Endpoint URL: https://api.together.ai/v1/chat/completions
    Authentication Type: API Key via HTTP Header
    Header Key: Authorization
    Header Value: Bearer <TOGETHER_API_KEY>
    Together AI authentication settings in TypingMind
  4. 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.

    Pricing settings in TypingMind for meta-models/Muse-Spark-Open-816B-A42B
  5. 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.

    Custom model capabilities settings in TypingMind
  6. Test and save

    Click "Test & Save" to verify the connection and add the model.

III

Start chatting with Muse Spark Open

Now you can start chatting with Muse Spark Open through TypingMind:

  • Select Muse Spark Open 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 Muse Spark Open from Together AI on TypingMind

💡 Pro tips for better results:

TypingMindTogether AI

Why TypingMind + Together AI?

Chat with Muse Spark Open and 200+ other models in one workspace, using your own Together AI API key.

Best-in-class UI

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

Model flexibility

Switch between Muse Spark Open and 200+ models instantly.

Cost control

Pay only for what you use through Together AI.

One-time purchase

Buy TypingMind once, use forever with any Together AI model.

Data privacy

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

Plugins, MCP, Skills & AI agents

Extend Muse Spark Open with web search, image generation, and custom AI agents.

Try TypingMind for free

Frequently Asked Questions

Do I need a subscription to use Muse Spark Open?

No. With your own Together AI 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 Muse Spark Open?

Muse Spark Open costs $1.25/1M input tokens and $4.25/1M output tokens via Together AI. A typical conversation costs around $0.01-0.10, depending on length.

Can I use other models besides Muse Spark Open?

Yes. Any model your Together AI 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 Muse Spark Open 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 Together AI with your API key, so check Together AI's data policy for how it handles API requests.

More models from Together AI