Nvidia
Inference hostNvidia runs open and licensed models on its own hardware and sells them by usage, often faster or cheaper than the maker.
Models78
- Cheapest for
- 0 models
- Serves
- 4 model types
Monthly visits—
Models by type
Models on Nvidia
| Model | Input | Output | vs official | Context |
|---|---|---|---|---|
 GLM-5.3Zhipu AI | Free/1M | Free/1M | -100% | — |
 DeepSeek V4.1 FlashDeepSeek | Free/1M | Free/1M | -100% | — |
| GLM-5.3-FlashZhipu AI | Free/1M | Free/1M | -100% | — |
 MiniMax-M3.1-FlashMiniMax | Free/1M | Free/1M | -100% | — |
| GPT OSS 20BOpenAI | Free/1M | Free/1M | -100% | — |
| Kimi K2.6Moonshot AI | Free/1M | Free/1M | -100% | — |
 Gemma 4Google | Free/1M | Free/1M | -100% | — |
| Nemotron 3.5 Lightning 30B A3BNVIDIA | Free/1M | Free/1M | Official | — |
| Gemma 3 4B ITGoogle | Free/1M | Free/1M | -100% | — |
| Nemotron 3.5 Embed 1BNVIDIAOnly here | Free/1M | Free/1M | Official | — |
| Nemotron 3.5 Bolt E4BNVIDIAOnly here | Free/1M | Free/1M | Official | — |
| Gemma 3 12B ITGoogle | Free/1M | Free/1M | -100% | — |
| Nemotron 3 Super 120B A12BNVIDIA | Free/1M | Free/1M | Official | — |
| Gemma 2BGoogleOnly here | Free/1M | Free/1M | — | — |
| Nemotron 3 Ultra 550B A55BNVIDIA | Free/1M | Free/1M | Official | — |
| Nemotron-4-340B-InstructNVIDIAOnly here | Free/1M | Free/1M | Official | — |
| Nemotron 3 Nano OmniNVIDIA | Free/1M | Free/1M | Official | — |
| Nemotron Parse 2.0NVIDIAOnly here | Free/1M | Free/1M | Official | — |
| Nemotron 3 Embed 1BNVIDIAOnly here | Free/1M | Free/1M | Official | — |
| Nemotron 3.5 Content SafetyNVIDIA | Free/1M | Free/1M | Official | — |
 Codestral 22B Instruct V0.1MistralOnly here | Free/1M | Free/1M | — | — |
 Ahm Phi 3.5 Moe InstructMicrosoft | Free/1M | Free/1M | -100% | — |
| Ai Synthetic Video DetectorNVIDIAOnly here | Free/1M | Free/1M | Official | — |
| Codegemma 1.1 7BGoogleOnly here | Free/1M | Free/1M | — | — |
| Codegemma 7BGoogleOnly here | Free/1M | Free/1M | — | — |
 Codellama 70BMetaOnly here | Free/1M | Free/1M | — | — |
| Cosmos Reason2 8BNVIDIAOnly here | Free/1M | Free/1M | Official | — |
| DeepSeek Coder 6.7B InstructDeepSeekOnly here | Free/1M | Free/1M | — | — |
| DeplotGoogleOnly here | Free/1M | Free/1M | — | — |
| DiffusionGemmaGoogleOnly here | Free/1M | Free/1M | — | — |
| Embed Qa 4NVIDIAOnly here | Free/1M | Free/1M | Official | — |
| Granite 3.0 3B A800m InstructIBMOnly here | Free/1M | Free/1M | — | — |
| Granite 3.0 8B InstructIBM | Free/1M | Free/1M | -100% | — |
| Granite 34B Code InstructIBMOnly here | Free/1M | Free/1M | — | — |
| Granite 8B Code InstructIBMOnly here | Free/1M | Free/1M | — | — |
| Ising Calibration 1.5 31BNVIDIAOnly here | Free/1M | Free/1M | Official | — |
| Jamba 1.5 LargeAI21 Labs | Free/1M | Free/1M | -100% | — |
| Kosmos 2MicrosoftOnly here | Free/1M | Free/1M | — | — |
 Laguna XS 2.1Poolside | Free/1M | Free/1M | -100% | — |
| Llama 3.1 Nemoguard 8B Content SafetyNVIDIAOnly here | Free/1M | Free/1M | Official | — |
| Llama 3.1 Nemoguard 8B Topic ControlNVIDIAOnly here | Free/1M | Free/1M | Official | — |
| Llama 3.1 Nemotron 51B InstructNVIDIAOnly here | Free/1M | Free/1M | Official | — |
| Llama 3.1 Nemotron 70B InstructNVIDIA | Free/1M | Free/1M | Official | — |
| Llama 3.1 Nemotron Safety Guard 8B V3NVIDIAOnly here | Free/1M | Free/1M | Official | — |
| Llama 3.1 Nemotron Ultra 253BNVIDIA | Free/1M | Free/1M | Official | — |
| Llama 3.2 11B Vision InstructMeta | Free/1M | Free/1M | -100% | — |
| Llama 3.2 Nemoretriever 1B Vlm Embed V1NVIDIAOnly here | Free/1M | Free/1M | Official | — |
| Llama 3.2 Nv Embedqa 1B V1NVIDIAOnly here | Free/1M | Free/1M | Official | — |
| Llama Guard 4 12BMeta | Free/1M | Free/1M | -100% | — |
| Llama Nemotron Embed VL 1B V2NVIDIAOnly here | Free/1M | Free/1M | Official | — |
Nvidia at a glance
78 models in total: 63 text, 9 embedding, 5 moderation, 1 video. GLM-5.3 has the largest context window, 1.05M tokens. The most searched is GLM-5.3, with about 276K Google searches a month. The newest is MiniMax-M3.1-Flash, released Oct 17, 2026.
Largest context
- GLM-5.31.05M
- DeepSeek V4.1 Flash1.05M
- GLM-5.3-Flash1.05M
- MiniMax-M3.1-Flash1.05M
Step 5 Preview1.05M
Most searched
- GLM-5.3276K
- DeepSeek V4.1 Flash138K
- GLM-5.3-Flash121K
- MiniMax-M3.1-Flash29K
- GPT OSS 20B12K
Newest
- MiniMax-M3.1-FlashOct 17, 2026
- Nemotron 3.5 Super VL 120B A12BOct 15, 2026
- Nemotron 3.5 Embed 1BOct 7, 2026
- Nemotron 3.5 Embed 8BOct 7, 2026
- Step 5 PreviewSep 20, 2026