Skip to main content

​
Overview

Together AI is an inference platform specializing in open-source models. It provides fast, cost-effective access to the best open-weight models including Llama, Mixtral, Qwen, and many more, with competitive pricing and high throughput.

​
Supported Models

Together AI frequently adds new open-source models as they are released. Check the model dropdown in EnConvo for the latest available models.

​
Setup

1

Get API Key

  1. Go to Together AI
  2. Sign in or create an account
  3. Navigate to Settings → API Keys
  4. Create a new API key
2

Configure in EnConvo

  1. Open Settings → AI Provider
  2. Select Together AI
  3. Go to Credentials module
  4. Enter your API key
3

Select Model

Choose your preferred model from the dropdown

​
Configuration

​
Validate and Use

1

Validate credentials

Click Validate in the Together AI credential settings. If validation fails, confirm the API key is active and your account has credits.
2

Start with a smaller model

Use smaller open models for quick testing before moving to larger models such as 70B or 405B variants.
3

Confirm model availability

Together AI frequently updates hosted models. If a model fails, select it from the EnConvo dropdown again or choose a nearby model family.

​
Pricing

Together AI offers competitive pricing for open-source models. Check Together AI Pricing for current rates.
New accounts receive free credits to get started. Together AI pricing is often significantly lower than commercial model providers.

​
Best Practices

  • Llama 3.1 405B: When you need maximum open-source quality
  • Llama 3.1 70B: Best balance of quality and cost for most tasks
  • Llama 3.1 8B: High-volume or latency-sensitive workloads
  • Mixtral 8x22B: Good general-purpose alternative
  • Qwen 2.5 72B: Excellent for multilingual and coding tasks
  • Start with smaller models and scale up only if needed
  • Use 8B models for simple tasks to save costs
  • Monitor usage in the Together AI dashboard

​
Troubleshooting

  • Verify the key is copied correctly from api.together.xyz
  • Check if your account has sufficient credits
  • Ensure the key has not been revoked
  • Some models may be temporarily offline for maintenance
  • Try a different model from the same family
  • Check Together AI status page for service updates
  • Larger models (405B) take longer to respond
  • Switch to a smaller model for faster inference
  • Check if Together AI is experiencing high load