695 listed
Models
Language models for agents: hosted models with input and output prices per million tokens from OpenRouter (read daily; prices change often), and open-weights models from Hugging Face with license and downloads. Filter by tool calling, context window and price, or switch to the table to compare.
Showing 1–21 of 21
| Model | Provider | Input $/M | Output $/M | Context | Tools | Weights |
|---|---|---|---|---|---|---|
| NVIDIA-Nemotron-3-Super-120B-A12B-BF16 | NVIDIA | Self-host | — | — | — | Open |
| Nemotron 3 Nano 30B A3Breasoning | NVIDIA | $0.06 | $0.24 | 262K | Yes | Open |
| Nemotron 3 Ultrareasoning | NVIDIA | $0.6 | $2.4 | 262K | Yes | Open |
| Nemotron 3.5 Lightningreasoning | NVIDIA | $0.07 | $0.2 | 262K | Yes | Open |
| NVIDIA-Nemotron-3.5-Bolt-E4B-BF16 | NVIDIA | Self-host | — | — | — | Open |
| NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16 | NVIDIA | Self-host | — | — | — | Open |
| Nemotron 3 Nano Omnireasoning | NVIDIA | Free | Free | 256K | Yes | Open |
| Nemotron 3 Superreasoning | NVIDIA | $0.3 | $2.4 | 262K | Yes | Open |
| Nemotron 3.5 Content Safetyreasoning | NVIDIA | $0.2 | $0.2 | 131K | — | Open |
| Nemotron 3.5 Super VLreasoning | NVIDIA | $0.15 | $0.5 | 1M | Yes | Open |
| gpt-oss-120b-Eagle3-short-context | NVIDIA | Self-host | — | — | — | Open |
| NVIDIA-Nemotron-3-Nano-4B-BF16 | NVIDIA | Self-host | — | — | Yes | Open |
| NVIDIA-Nemotron-Nano-9B-v2 | NVIDIA | Self-host | — | — | — | Open |
| Nemotron-Cascade-2-30B-A3B | NVIDIA | Self-host | — | — | — | Open |
| Llama-3_3-Nemotron-Super-49B-v1_5 | NVIDIA | Self-host | — | — | — | Open |
| Nemotron-Orchestrator-8B | NVIDIA | Self-host | — | — | — | Open |
| Llama-3_3-Nemotron-Super-49B-v1 | NVIDIA | Self-host | — | — | — | Open |
| Llama-3.1-Nemotron-70B-Instruct-HF | NVIDIA | Self-host | — | — | — | Open |
| Llama3-ChatQA-1.5-8B | NVIDIA | Self-host | — | — | — | Open |
| Llama-3_1-Nemotron-Ultra-253B-v1 | NVIDIA | Self-host | — | — | — | Open |
| Llama3-ChatQA-1.5-70B | NVIDIA | Self-host | — | — | — | Open |
Prices are USD per million tokens from OpenRouter, read daily. Providers change prices often; check the model page before you rely on one.