NVIDIA
Open-weight labwww.nvidia.com/en-us/ai/
Models
47
not retired
Lineup
5
last 18 months
Hosts
15
Retiring
2
next 12 months
Current lineup
General-purpose models released in the last 18 months, newest first. Prices are the lab's own, per million tokens.
| Model | In / out per 1M | Released | Capabilities |
|---|---|---|---|
| $0.30 / $0.90 via Nebius AI Studio | Oct 2026 | Reasoning · Tools · Vision | |
| $0.06 / $0.24 via Nebius AI Studio | Aug 2026 | Reasoning · Tools | |
| - | Jun 2026 | ||
| - | Jun 2026 | ||
| $0.05 / $0.20 via DeepInfra | Dec 2025 | Reasoning · Tools · Caching |
Being retired
Dates announced by an API host in the next 12 months.
- Nemotron Nano 12BNVIDIA · on Amazon Bedrockin 131 days30 Mar 2027
- Nemotron Nano 9BNVIDIA · on Amazon Bedrockin 131 days30 Mar 2027
Images, audio, search and more
| Model | In / out per 1M | Released | Capabilities |
|---|---|---|---|
Moderation | - | - | |
Embedding | - | - | |
Embedding | - | - | |
Embedding | - | - |
Older models
Superseded or undated, but still served somewhere.
Show 38 older models
| Model | In / out per 1M | Released | Capabilities |
|---|---|---|---|
Chat | - | Mar 2026 | |
Chat | - | - | |
Chat | $0.50 / $2.15 via W&B Inference | - | Reasoning · Caching |
Chat | $0.10 / $0.50 via GMI Cloud | - | |
Chat | $0.04 / $0.16 via DeepInfra | - | Tools |
Chat | - | - | |
Chat | - | - | |
Chat | $0.07 / $0.20 via W&B Inference | - | Reasoning · Caching |
Chat | $0.15 / $0.50 via DeepInfra | - | Reasoning · Tools · Vision · Structured |
Chat | $0.66 / $2.64 via Azure AI Foundry | - | Reasoning · Tools · Caching |
Chat | $0.06 / $0.22 via Azure AI Foundry | - | Reasoning · Tools · Caching |
Chat | - | - | |
Chat | $0.10 / $0.40 via Nebius AI Studio | - | Tools |
Chat | $0.10 / $0.40 via DeepInfra | - | Tools |
Chat | $0.12 / $0.30 via Lambda AI | - | Tools |
Chat | $0.50 / $1.50 via Cloudflare Workers AI | - | Reasoning · Tools |
Embedding | - | - | |
Chat | $0.06 / $0.24 via Nebius AI Studio | - | Reasoning · Tools · Vision |
Chat | - | - | |
Chat | $0.675 / $3.38 via Kyma API | - | Reasoning · Tools · Structured · Caching |
Chat | - | - | Tools · Structured |
Chat | $0.20 / $0.50 via Perplexity | - | |
Chat | - | - | Tools · Structured |
Chat | - | - | |
Chat | - | - | |
Chat | $0.20 / $0.20 via DeepInfra | - | Vision |
Chat | $0.20 / $0.60 via Amazon Bedrock | - | Tools · Vision · Structured |
Chat | $0.06 / $0.24 via Amazon Bedrock | - | Tools · Structured |
Chat | - | - | |
Chat | $0.06 / $0.23 via Amazon Bedrock | - | Tools · Structured |
Chat | $0.10 / $0.10 via Fireworks AI | - | |
Chat | - | - | |
Chat | - | - | |
Chat | $0.15 / $0.65 via Amazon Bedrock | - | Reasoning · Tools · Structured |
Chat | $0.06 / $0.24 via Nebius AI Studio | - | Reasoning · Tools |
Chat | $0.075 / $0.40 via DeepInfra | - | Reasoning · Tools · Structured |
Chat | $0.06 / $0.16 via DeepInfra | - | Reasoning · Tools · Caching |
Chat | $0.20 / $0.20 via Fireworks AI | - |
Where to run NVIDIA models
Hosts by how many of its models they serve.