Bring Your Own LLM: A Decision Framework

If you are buying a business platform that uses AI, you are also making a model decision. Often without realizing it.

Most platforms ship one model behind the scenes. The platform vendor chose it. You inherit the trade-offs — cost, latency, quality, data-residency, model behavior, and the supplier relationship the vendor has with the model provider.

There is another way. Bring your own LLM (BYO LLM) lets you choose the model per workload and pay through your own provider relationship. Atlas supports this natively. This essay is a decision framework for whether and how to use it.

When BYO LLM is the right call

Three customer profiles for whom BYO LLM is the clear answer:

1. The privacy-led organization. If your data has unusual residency requirements — regulated industry, government contract, data-localization law — you may already have a vetted LLM relationship (often through Microsoft Azure OpenAI, AWS Bedrock, or a private Anthropic agreement). BYO LLM lets you keep that relationship and use Atlas on top.

2. The cost-optimized organization. Large LLM users typically negotiate enterprise pricing directly with model providers. BYO LLM lets you keep the negotiated discount; the platform vendor does not become the middleman.

3. The multi-model organization. Some workloads work better on Claude. Some work better on GPT. Some are fine on a small local Ollama model. BYO LLM lets you route per workload — and lets you migrate when models change.

When BYO LLM is overkill

Equally honest about when it's not necessary:

• You're a 10-person company without a vetted model relationship. Use the platform vendor's default model.
• Your AI usage is light (under a million tokens per month). The cost difference is not worth the operational overhead.
• Your team doesn't have a clear policy on which model is preferred. Start with one; iterate when you have signal.

How Atlas handles it

Atlas's LLM provider abstraction supports Anthropic Claude, OpenAI GPT, GitHub Models, and local Ollama out of the box. You configure per-tier: which model handles drafting, which handles summarization, which handles analysis. Per-call token usage is metered against the org and attributed to the user or agent that triggered it.

You can switch providers without changing your workflows. The Atlas tool surface is provider-agnostic — the same tool calls work against any provider.

What to think about before adopting BYO LLM

• Quality. Have you tested your primary workloads on the model you're considering? Model quality varies materially across providers.
• Latency. Some providers are faster than others. Workspace assistant interactions are user-facing; latency matters.
• Reliability. Providers have outages. Have a fallback configured.
• Cost. Token pricing changes. Plan for it.
• Data terms. Read the provider's data-retention and training-data clauses carefully. Atlas does not train on your data; your provider's policy is separate.

Our take

For most teams under 100 people, the platform's default model is the right starting point. Switch to BYO LLM the moment any of the three customer profiles above starts to describe you. Atlas is built to make the switch a configuration change, not a migration.