| cosmos-predict1-5b | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 0 | – | – | aggregator | modelsdev |
| Llama 3.1 Nemotron Nano VL 8B v1 | meta | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 32768 | – | – | aggregator | modelsdev |
| studiovoice | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| nemotron-content-safety-reasoning-4b | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| llama-3.1-nemotron-safety-guard-8b-v3 | meta | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| nv-embed-v1 | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 32768 | – | – | aggregator | modelsdev |
| synthetic-video-detector | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 0 | – | – | aggregator | modelsdev |
| cosmos-transfer2.5-2b | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 0 | – | – | aggregator | modelsdev |
| Nemotron 3 Nano Omni 30B A3B Reasoning | openrouter | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 256000 | – | – | aggregator | modelsdev |
| Llama 3.1 Nemotron Nano 8B v1 | meta | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | modelsdev |
| Active Speaker Detection | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 0 | – | – | aggregator | modelsdev |
| streampetr | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| llama-nemotron-rerank-vl-1b-v2 | meta | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| nemotron-mini-4b-instruct | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| Cosmos Reason2 8B | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | modelsdev |
| nemotron-3-content-safety | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| Llama 3.3 Nemotron Super 49B v1.5 | nvidia | nvidia | – | freefree | freefree | freefree | –n/a | –n/a | –n/a | –n/a | 131072 | llama3 | – | aggregator | modelsdev |
| magpie-tts-zeroshot | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 0 | – | – | aggregator | modelsdev |
| riva-translate-4b-instruct-v1_1 | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| Nemotron Nano 12B v2 VL | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| Nemotron 3.5 Content Safety | openrouter | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| Llama 3.3 Nemotron Super 49B v1.5 | meta | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | modelsdev |
| llama-3_2-nemoretriever-300m-embed-v1 | meta | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 32768 | – | – | aggregator | modelsdev |
| gliner-pii | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| usdcode | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| usdvalidate | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 0 | – | – | aggregator | modelsdev |
| Llama 3.1 Nemotron 70B Instruct | meta | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| rerank-qa-mistral-4b | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| Qwen Image Edit | alibaba | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 0 | – | – | aggregator | modelsdev |
| Qwen3 Coder 480B A35B Instruct | alibaba | nvidia | – | freefree | freefree | freefree | –n/a | –n/a | –n/a | –n/a | 262144 | qwen2 | – | aggregator | modelsdev |
| Qwen3.5-122B-A10B | openrouter | nvidia | – | freefree | freefree | freefree | –n/a | –n/a | –n/a | –n/a | 262144 | qwen2 | – | aggregator | modelsdev |
| Qwen3 Next 80B A3B Instruct | openrouter | nvidia | – | freefree | freefree | freefree | –n/a | –n/a | –n/a | –n/a | 262144 | qwen2 | – | aggregator | modelsdev |
| Qwen3.5-397B-A17B | openrouter | nvidia | – | freefree | freefree | freefree | –n/a | –n/a | –n/a | –n/a | 262144 | qwen2 | – | aggregator | modelsdev |
| Qwen2.5 Coder 32b Instruct | alibaba | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| Qwen Image | alibaba | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 0 | – | – | aggregator | modelsdev |
| Whisper Large v3 | nvidia | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 0 | – | – | aggregator | modelsdev |
| gpt-oss-20b (GovCloud) | openrouter | nvidia | – | freefree | freefree | freefree | –n/a | –n/a | –n/a | –n/a | 131072 | o200k | – | aggregator | modelsdev |
| Phi-4-Mini | microsoft | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | modelsdev |
| Phi 4 Multimodal | microsoft | nvidia | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | modelsdev |
| Devstral Small 2 | mistral | mistral | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 256000 | – | – | aggregator | modelsdev |
| DeepSeek R1 Distill Llama 8B | deepseek | alibaba | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 32768 | – | – | aggregator | modelsdev |
| DeepSeek R1 Distill Qwen 1.5B | deepseek | alibaba | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | 32768 | – | – | aggregator | modelsdev |
| prism-ml-ternary-bonsai-27b | together | together | – | freen/a | freen/a | freen/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-together |
| accounts/fireworks/models/flux-1-dev-controlnet-union | fireworks | fireworks | – | 0.0010n/a | 0.0010n/a | 0.0010n/a | –n/a | –n/a | –n/a | –n/a | 4096 | – | – | aggregator | litellm |
| juggernaut-lightning-flux | together | together | – | 0.0017n/a | –n/a | 0.0017n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-together |
| sd-xl | together | together | – | 0.0019n/a | –n/a | 0.0019n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-together |
| juggernaut-pro-flux | together | together | – | 0.0049n/a | –n/a | 0.0049n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-together |
| qwen-image | together | together | – | 0.0058n/a | –n/a | 0.0058n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-together |
| Qwen3-Embedding-8B | alibaba | nebius | – | 0.0100n/a | freen/a | 0.0075n/a | –n/a | –n/a | –n/a | –n/a | 40960 | – | – | aggregator | modelsdev |
| Qwen/Qwen2.5-Coder-7B | alibaba | nebius | – | 0.0100n/a | 0.0300n/a | 0.0150n/a | –n/a | –n/a | –n/a | –n/a | 32768 | – | – | aggregator | litellm |