Question 1

How many AI models does Nemo Router support?

Accepted Answer

Nemo Router currently serves 97+ live models across Anthropic (Claude Opus 4.8, Sonnet 4.6, Haiku 4.5), Google Vertex AI (Gemini 3.5 Flash, Gemini 3.1 Pro, Imagen, Veo, embeddings), and OpenAI (GPT-5.5, GPT-4o, o-series). AWS Bedrock is 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: 0% platform fee on Tier 3 annual ($1,200+/yr). You pay only the provider cost. OpenRouter charges 5.5% on top of every call. Three tiers total: 4% pay-as-you-go, 2% on Tier 2 monthly ($100+/mo), 0% on Tier 3 annual ($1,200+/yr). 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.

78+ models. One key.