What models run on NVIDIA NIM?
124 models in the o10 catalog are configured on NVIDIA NIM.
124 routes in catalog.
o10Last updated 2026-07-26
NVIDIA NIM models
124 models routed through NVIDIA NIM (Prepaid billing).
Browse models with upstream IDs and pricing where available for the NVIDIA NIM fulfillment host.
Dashboards observe.
o10 enforces.
o10 enforces.
Every page in this index follows the same structure as the home site — answer-first, passage blocks, operational steps, and expanded FAQs. o10 State of Inference Spend 2026 found up to 638× compliant price spread across venues for identical workloads.
Start hereQuick overview
How to use this index
01 Ai Yi Large
C1
Abacusai Dracarys Llama 3 1 70b Instruct
C2
Adept Fuyu 8b
C0
Ai21labs Jamba 1 5 Large Instruct
C1
Aisingapore Sea Lion 7b Instruct
C1
Baai Bge M3
C1
Bigcode Starcoder2 15b
C1
Bytedance Seed Oss 36b Instruct
C1
Databricks Dbrx Instruct
C1
Ai Deepseek Coder 6 7b Instruct
C1
Ai Deepseek V4 Flash
C0
Ai Deepseek V4 Pro
C2
Codegemma 1 1 7b
C1
Codegemma 7b
C1
Deplot
C1
Diffusiongemma 26b A4b It
C1
Gemma 2 2b It
C1
Gemma 2b
C1
Gemma 3 12b It
C1
Gemma 3 4b It
C1
Gemma 3n E2b It
C1
Gemma 3n E4b It
C1
Gemma 4 31b It
C0 · $0.14/M
Recurrentgemma 2b
C1
Ibm Granite 3 0 3b A800m Instruct
C0
Ibm Granite 3 0 8b Instruct
C0
Ibm Granite 34b Code Instruct
C1
Ibm Granite 8b Code Instruct
C0
Codellama 70b
C2
Llama 3 1 70b Instruct
C2
Llama 3 1 8b Instruct
C0
Llama 3 2 11b Vision Instruct
C0
Llama 3 2 1b Instruct
C0
Llama 3 2 3b Instruct
C0
Llama 3 2 90b Vision Instruct
C1
Llama 3 3 70b Instruct
C2
Llama 4 Maverick 17b 128e Instruct
C1
Llama Guard 4 12b
C1
Llama2 70b
C2
Microsoft Kosmos 2
C0
Microsoft Phi 3 5 Moe Instruct
C0
Microsoft Phi 3 Vision 128k Instruct
C0
Microsoft Phi 4 Mini Instruct
C0
Microsoft Phi 4 Multimodal Instruct
C0
Minimaxai Minimax M2 7
C3
Minimaxai Minimax M3
C3
Mistralai Codestral 22b Instruct V0 1
C1 · $0.3/M
Mistralai Ministral 14b Instruct 2512
C0
Mistralai Mistral 7b Instruct V0 3
C1
Mistralai Mistral Large
C1
Mistralai Mistral Large 2 Instruct
C1
Mistralai Mistral Large 3 675b Instruct 2512
C1
Mistralai Mistral Medium 3 5 128b
C2
Mistralai Mistral Nemotron
C1
Mistralai Mistral Small 4 119b 2603
C0 · $0.1/M
Mistralai Mixtral 8x22b V0 1
C1
Mistralai Mixtral 8x7b Instruct V0 1
C1
Moonshotai Kimi K2 6
C1 · $0.95/M
Nemotron 3 Nano 30b A3b
C2 · $0.05/M
Nemotron 3 Super 120b A12b
C4 · $0.15/M
Nemotron Nano 9b V2
C2 · $0.06/M
Nv Mistralai Mistral Nemo 12b Instruct
C1
Nvidia Ai Synthetic Video Detector
C0
Nvidia Cosmos Reason2 8b
C0
Nvidia Embed Qa 4
C0
Nvidia Gliner Pii
C1
Nvidia Ising Calibration 1 35b A3b
C0
Nvidia Llama 3 1 Nemoguard 8b Content Safety
C0
Nvidia Llama 3 1 Nemoguard 8b Topic Control
C0
Nvidia Llama 3 1 Nemotron 51b Instruct
C0
Nvidia Llama 3 1 Nemotron 70b Instruct
C2
Nvidia Llama 3 1 Nemotron Nano 8b V1
C0
Nvidia Llama 3 1 Nemotron Nano Vl 8b V1
C0
Nvidia Llama 3 1 Nemotron Safety Guard 8b V3
C0
Nvidia Llama 3 1 Nemotron Ultra 253b V1
C3
Nvidia Llama 3 2 Nemoretriever 1b Vlm Embed V1
C0
Nvidia Llama 3 2 Nv Embedqa 1b V1
C0
Nvidia Llama 3 3 Nemotron Super 49b V1
C1
Nvidia Llama 3 3 Nemotron Super 49b V1 5
C1
Nvidia Llama Nemotron Embed 1b V2
C0
Nvidia Llama Nemotron Embed Vl 1b V2
C0
Nvidia Llama3 Chatqa 1 5 70b
C2
Nvidia Mistral Nemo Minitron 8b 8k Instruct
C0
Nvidia Nemoretriever Parse
C1
Nvidia Nemotron 3 5 Content Safety
C1
Nvidia Nemotron 3 Content Safety
C1
Nvidia Nemotron 3 Nano 30b A3b
C0 · $0.05/M
Nvidia Nemotron 3 Nano Omni 30b A3b Reasoning
C3
Nvidia Nemotron 3 Super 120b A12b
C1 · $0.15/M
Nvidia Nemotron 3 Ultra 550b A55b
C3 · $0.6/M
Nvidia Nemotron 4 340b Instruct
C1
Nvidia Nemotron 4 340b Reward
C1
Nvidia Nemotron Content Safety Reasoning 4b
C3
Nvidia Nemotron Mini 4b Instruct
C0
Nvidia Nemotron Nano 12b V2 Vl
C0 · $0.2/M
Nvidia Nemotron Nano 3 30b A3b
C0
Nvidia Nemotron Parse
C1
Nvidia Neva 22b
C1
Nvidia Nv Embed V1
C0
Nvidia Nv Embedcode 7b V1
C0
Nvidia Nv Embedqa E5 V5
C0
Nvidia Nv Embedqa Mistral 7b V2
C0
Nvidia Nvclip
C1
Nvidia Nvidia Nemotron Nano 9b V2
C0
Nvidia Riva Translate 4b Instruct
C1
Nvidia Riva Translate 4b Instruct V1 1
C1
Nvidia Vila
C1
Gpt Oss 120b
C1 · $0.35/M
Gpt Oss 20b
C1 · $0.05/M
Qwen Qwen3 5 122b A10b
C1
Qwen Qwen3 5 397b A17b
C1
Qwen Qwen3 Next 80b A3b Instruct
C0
Sarvamai Sarvam M
C1
Snowflake Arctic Embed L
C0
Stepfun Ai Step 3 5 Flash
C0
Stepfun Ai Step 3 7 Flash
C0
Stockmark Stockmark 2 100b Instruct
C1
Upstage Solar 10 7b Instruct
C1
Writer Palmyra Creative 122b
C1
Writer Palmyra Fin 70b 32k
C2
Writer Palmyra Med 70b
C2
Writer Palmyra Med 70b 32k
C2
Z Ai Glm 5 1
C1
Zyphra Zamba2 7b Instruct
C1
FAQFrequently asked questions
Common questions
How many models on NVIDIA NIM?
124 unique o10 slugs.
Where does pricing come from?
Gateway snapshot where joined; otherwise see model profile for host routes.
o10Set the envelope. o10 holds it.
See what you're overpaying.
Paste a week of traffic. Get the number that books the audit.
See what you're overpaying →