Question 1

How many AI models does Nemo Router support?

Accepted Answer

Nemo Router currently serves 20+ live models on Google Vertex AI (Gemini 2.5 Pro, Flash, Imagen, Veo, embeddings). Anthropic (Claude Opus 4, Sonnet 4, Haiku), OpenAI (GPT-4o, GPT-5.3, o1), and AWS Bedrock are shipping next. New models are added within days of release.

Question 2

Can I switch between models without changing code?

Accepted Answer

Yes. Nemo Router uses an OpenAI-compatible API. Just change the model parameter in your request — no code changes, no provider SDK swaps. All models work through the same API endpoint.

Question 3

How is model pricing calculated on Nemo Router?

Accepted Answer

You pay the provider cost per token (input and output). Nemo Router adds a platform fee on top: 4% on Tier 1 (Pay As You Go), 2% on Tier 2 (monthly $100+), 0% on Tier 3 (annual $1,200+). We never markup provider costs beyond the platform fee.

Question 4

What is the cheapest way to use GPT-4o or Claude?

Accepted Answer

Through Nemo Router on a Tier 3 annual plan ($1,200+/yr): 0% platform fee. You pay only the provider cost. OpenRouter charges 5-15% on top of every call. Tier 2 monthly is 2%, pay-as-you-go is 4% — still cheaper than OpenRouter on every model.

Question 5

Do you support fine-tuned models?

Accepted Answer

Yes. You can use fine-tuned OpenAI models and custom deployments through Nemo Router. Configure your fine-tuned model ID in your API requests as you would with the provider directly.

20+ models. One key.