Skip to main content
Enclave
English
Start free
Model integrations

Use Together AI in Enclave (cloud-hosted open models)

Enclave supports Together AI via BYOK: enter your Together API key to use its many cloud-hosted open-source models (Llama, Qwen, Mixtral, etc.) as the base for Enclave characters. It suits users who want open models without operating GPUs themselves. Enclave doesn't resell quota and bills at Together's official rates.

Last reviewed:

The short answer

Enter your Together AI API key and Enclave's characters reply with cloud-hosted open-source models—no GPU management.

Key points at a glance

  • BYOK: use your own Together account and quota.
  • One endpoint reaches a large set of open-source models—no need to build your own GPU inference.
  • A middle ground for "I want open models but don't want to operate them."

How to connect

In model settings choose an OpenAI-compatible provider, enter your Together API key, point the base URL at Together's endpoint, pick a specific model name, then set it as default or assign per character.

Who it's for

Users who want the flexibility of open models but don't want to buy and operate their own GPUs. With Enclave self-hosted, your data stays under your control while inference runs on Together's cloud.

Key facts

Integration
BYOK (OpenAI-compatible endpoint)
Billing
Billed at Together's official rates; no Enclave markup
Best for
Cloud-hosted open models, no GPU ops
Data flow
Direct from your instance when self-hosted

Ready to try it?

Open it in your browser — no credit card, no install.

Start freeLearn about self-hosting

Related

Connect other models

Use Together AI in Enclave (cloud-hosted open models) · Enclave