Bring Your Own LLM
Claude. GPT.
Gemini. Open models.
Your choice.
Use the models you trust. Plug in your own API keys for Anthropic, OpenAI, Google, Mistral and more, or point VectorLumira at your own endpoints and self-hosted models.
Claude
Anthropic
Careful tool use, coding and long tasks.
- Your API key, encrypted at rest
- Billed directly by your provider
- Automatic fallback on outages
# agent: support-triage
model: anthropic/claude
api_key: {{ secrets.MY_KEY }}
fallback: openai/gpt
temperature: 0.2
max_cost_per_run: $0.05Every model. Your keys.
What you get with Bring Your Own LLM.
All major providers
Anthropic, OpenAI, Google, Mistral, Meta Llama, DeepSeek, xAI, Cohere and more.
Your own endpoints
Azure OpenAI, AWS Bedrock, Google Vertex, or any OpenAI-compatible server like vLLM and Ollama.
Per-step choice
Use a fast model to classify and a frontier model to reason, in the same workflow.
Fallbacks
If a provider is down or rate-limited, route to a backup model automatically.
Keys stay yours
Keys are encrypted, scoped per workspace, and usage is billed directly by your provider.
Questions
Do I need my own keys?+
No. You can start with VectorLumira-managed models, then switch to your own keys whenever you like.
Start building today.
From $5 per user per month. Bring your own models. Connect everything in one click.