Latest offers SiliconFlow: SiliconFlow new-account $1 free credits View all →
← Brands
NVIDIA

NVIDIA

Multi-model API provider · Usage-based billing

NVIDIA develops Nemotron models. NVIDIA NIM offers development endpoints and self-hosted inference. Free testing is not a free commercial API; partner quotes belong to each partner.

Usage-based API; see model prices.

Listed models · 9

Distinct model versions are listed once; aliases are not additional models. Prices below are for API usage.

Nemotron 3.5 Lightning 30B A3B

API models and prices · 1

Usage-based billing: text rates are usually per million tokens; other units and tiers are stated per entry. Compare only the same currency, unit and billing conditions. Unverified cache pricing does not mean free.

Nemotron 3.5 Lightning 30B A3B

Official model ID: nvidia/nemotron-3.5-lightning-30b-a3b

Model developer: NVIDIA · Service provider: Self-hosted · Market: com

Model family: Nemotron · Model catalog only; see service-channel quotes

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model context: 1,048,576 tokens

Input / output modalities: text → text

Official source · Last verified: 2026-10-15T09:39:42.692Z

Capabilities and usage limits

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model details and channels → Official model documentation ↗

Nemotron Nano 9B V2

API models and prices · 1

Usage-based billing: text rates are usually per million tokens; other units and tiers are stated per entry. Compare only the same currency, unit and billing conditions. Unverified cache pricing does not mean free.

Nemotron Nano 9B V2

Official model ID: nvidia/nvidia-nemotron-nano-9b-v2

Model developer: NVIDIA · Service provider: Self-hosted · Market: com

Model family: Nemotron · Model catalog only; see service-channel quotes

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model context: 131,072 tokens

Input / output modalities: text → text

Official source · Last verified: 2026-10-15T09:39:43.330Z

Capabilities and usage limits

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model details and channels → Official model documentation ↗

Nemotron Nano 12B V2 VL

API models and prices · 1

Usage-based billing: text rates are usually per million tokens; other units and tiers are stated per entry. Compare only the same currency, unit and billing conditions. Unverified cache pricing does not mean free.

Nemotron Nano 12B V2 VL

Official model ID: nvidia/nemotron-nano-12b-v2-vl

Model developer: NVIDIA · Service provider: Self-hosted · Market: com

Model family: Nemotron · Model catalog only; see service-channel quotes

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model context: 131,072 tokens

Input / output modalities: text, image, video → text

Official source · Last verified: 2026-10-15T09:39:44.487Z

Capabilities and usage limits

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model details and channels → Official model documentation ↗

Nemotron 3 Super 120B A12B

API models and prices · 1

Usage-based billing: text rates are usually per million tokens; other units and tiers are stated per entry. Compare only the same currency, unit and billing conditions. Unverified cache pricing does not mean free.

Nemotron 3 Super 120B A12B

Official model ID: nvidia/nemotron-3-super-120b-a12b

Model developer: NVIDIA · Service provider: Self-hosted · Market: com

Model family: Nemotron · Model catalog only; see service-channel quotes

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model context: 1,048,576 tokens

Input / output modalities: text → text

Official source · Last verified: 2026-10-15T09:39:45.277Z

Capabilities and usage limits

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model details and channels → Official model documentation ↗

Nemotron 3 Nano Omni 30B A3B Reasoning

API models and prices · 1

Usage-based billing: text rates are usually per million tokens; other units and tiers are stated per entry. Compare only the same currency, unit and billing conditions. Unverified cache pricing does not mean free.

Nemotron 3 Nano Omni 30B A3B Reasoning

Official model ID: nvidia/nemotron-3-nano-omni-30b-a3b-reasoning

Model developer: NVIDIA · Service provider: Self-hosted · Market: com

Model family: Nemotron · Model catalog only; see service-channel quotes

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model context: 262,144 tokens

Input / output modalities: video, audio, image, text → text

Official source · Last verified: 2026-10-15T09:39:46.039Z

Capabilities and usage limits

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model details and channels → Official model documentation ↗

Nemotron 3 Ultra 550B A55B

API models and prices · 1

Usage-based billing: text rates are usually per million tokens; other units and tiers are stated per entry. Compare only the same currency, unit and billing conditions. Unverified cache pricing does not mean free.

Nemotron 3 Ultra 550B A55B

Official model ID: nvidia/nemotron-3-ultra-550b-a55b

Model developer: NVIDIA · Service provider: Self-hosted · Market: com

Model family: Nemotron · Model catalog only; see service-channel quotes

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model context: 1,048,576 tokens

Input / output modalities: text → text

Official source · Last verified: 2026-10-15T09:39:47.047Z

Capabilities and usage limits

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model details and channels → Official model documentation ↗

Nemotron 3.5 Content Safety

API models and prices · 1

Usage-based billing: text rates are usually per million tokens; other units and tiers are stated per entry. Compare only the same currency, unit and billing conditions. Unverified cache pricing does not mean free.

Nemotron 3.5 Content Safety

Official model ID: nvidia/nemotron-3.5-content-safety

Model developer: NVIDIA · Service provider: Self-hosted · Market: com

Model family: Nemotron · Model catalog only; see service-channel quotes

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model context: 131,072 tokens

Input / output modalities: text, image → text

Official source · Last verified: 2026-10-15T09:39:48.127Z

Capabilities and usage limits

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model details and channels → Official model documentation ↗

Nemotron 3 Nano 30B A3B

API models and prices · 1

Usage-based billing: text rates are usually per million tokens; other units and tiers are stated per entry. Compare only the same currency, unit and billing conditions. Unverified cache pricing does not mean free.

Nemotron 3 Nano 30B A3B

Official model ID: nvidia/nemotron-3-nano-30b-a3b

Model developer: NVIDIA · Service provider: Self-hosted · Market: com

Model family: Nemotron · Model catalog only; see service-channel quotes

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model context: 262,144 tokens

Input / output modalities: text → text

Official source · Last verified: 2026-10-15T09:39:48.978Z

Capabilities and usage limits

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model details and channels → Official model documentation ↗

Nemotron 3.5 Super VL 120B A12B

API models and prices · 1

Usage-based billing: text rates are usually per million tokens; other units and tiers are stated per entry. Compare only the same currency, unit and billing conditions. Unverified cache pricing does not mean free.

Nemotron 3.5 Super VL 120B A12B

Official model ID: nvidia/nemotron-3.5-super-vl-120b-a12b

Model developer: NVIDIA · Service provider: Self-hosted · Market: com

Model family: Nemotron · Model catalog only; see service-channel quotes

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model context: 262,144 tokens

Input / output modalities: text, image, video → text

Official source · Last verified: 2026-10-15T23:07:09.966Z

Capabilities and usage limits

Development, research or evaluation under the official terms only; not a free commercial API. Commercial hosted token rates are not published. Model licenses, deployment software licenses and infrastructure costs are separate.

Model details and channels → Official model documentation ↗