Model Catalog
10Nemo Router provides access to 200+ large language models from OpenAI, Anthropic, Google, Mistral, Meta, Cohere, and more — all through a single OpenAI-compatible API endpoint. 0% platform fee for life for founding customers (first 100K, offer ends August 2026).
Browse and compare models below. Filter by capability, sort by cost or context window. See pricing per model | Get started in 5 minutes
Claude 3 Haiku
200.0K
4.1K
$0.25
$1.25
Claude 3.5 Sonnet
200.0K
8.2K
$3.00
$15.00
Command R+
128.0K
4.1K
$2.50
$10.00
DeepSeek V3
131.1K
8.2K
$0.27
$1.10
Gemini 1.5 Flash
1.0M
8.2K
$0.075
$0.30
Gemini 1.5 Pro
2.1M
8.2K
$1.25
$5.00
GPT-4o
128.0K
16.4K
$2.50
$10.00
GPT-4o Mini
128.0K
16.4K
$0.15
$0.60
Llama 3.1 405B
131.1K
4.1K
$3.50
$3.50
Mistral Large
128.0K
4.1K
$2.00
$6.00
Frequently asked questions
Common questions about using models through Nemo Router.
Over 200 models from 15+ providers including OpenAI, Anthropic, Google, Mistral, Meta, Cohere, and more. We add new models within days of release.
Yes. Since all models are accessed through the same OpenAI-compatible API endpoint, you just change the model name in your request. No SDK changes, no endpoint changes.
Each model has per-token pricing set by the provider. Nemo Router charges 0% platform fee for life for the first 100,000 customers — you pay exactly provider cost. You can see exact pricing per model in the catalog above.
With Nemo Router you get one API key for all models from OpenAI, Anthropic, Google, and more — plus built-in cost tracking, team management, guardrails, and automatic failover. Direct provider access requires separate accounts, keys, and billing for each provider.
Yes. If you have fine-tuned a model with a provider (like OpenAI or Anthropic), you can route through Nemo Router using your fine-tuned model ID. Contact support for setup.