Any model · one work layer
Use any model. Keep the same work.
NOME routes to the frontier model you choose while your memory, context, approvals, artifacts, and receipts stay the same. The model can change; the work survives.
OpenAI
GPT · Codex
Anthropic
Claude
Google Gemini
Gemini · Vertex
DeepSeek
DeepSeek V4
xAI Grok
Grok
Meta Llama
Llama
Mistral
Mistral
MiniMax
MiniMax
Bring your own provider subscription, use your API keys, or use NOME’s hosted lane. Model availability depends on your connected providers.
How routing works
1 · Choose the model
Pick any provider per task — or let NOME pick. Switch models mid-thread without losing context.
2 · Choose the host & auth
Run through a provider seat on your trusted host, your own API key, or NOME's hosted lane.
3 · Keep the work
Memory, context, approvals, artifacts, and receipts are the same no matter which model answered.