# NVIDIA models

Canonical HTML page: [NVIDIA models](<https://impossibl.com/nvidia>)
Markdown alternative: [NVIDIA models as Markdown](<https://impossibl.com/nvidia.md>)

Access 1 model from NVIDIA through the Impossibl API, including Nemotron 3.5 Lightning. Compare API pricing, context windows, and capabilities.

Select two or three models to [compare specifications and API costs](<https://impossibl.com/compare.md>). Model types and billing units are not interchangeable.

## Models

### [Nemotron 3.5 Lightning](<https://impossibl.com/nvidia/nemotron-3.5-lightning>)

Nemotron 3.5 Lightning is a text generation model from NVIDIA, available through the Impossibl API. Its published context window is 262,144 tokens. The advertised input rate is $0.05 per million input tokens. The advertised output rate is $0.20 per million output tokens.

- API identifier: `nvidia/nemotron-3.5-lightning`
- Creator: NVIDIA; model type: Text generation.
- Context window: 262,144 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.05 per million input tokens; $0.20 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/nvidia/nemotron-3.5-lightning.md>)

## Frequently asked questions

### Which NVIDIA models are available through Impossibl?

The directory lists 1 model from NVIDIA available through the Impossibl API, including Nemotron 3.5 Lightning. Open each model page for its API identifier, capabilities, and current pricing.

### How much do NVIDIA models cost?

NVIDIA model prices vary by model and usage. All rates below are published base API rates in USD. For token-priced models, published input rates start at $0.05 per million input tokens. Published output rates start at $0.20 per million output tokens. Input and output minima may refer to different models. Individual model pages include published cache prices and billing units. Applicable fees and workspace-specific pricing can affect the amount paid.

### What context windows do NVIDIA models support?

Among NVIDIA models with a published limit on Impossibl, the largest context window is 262,144 tokens, listed for Nemotron 3.5 Lightning. Context limits vary by model and are separate from maximum output limits.

### What inputs and capabilities do NVIDIA models support?

Available model types include text generation. Published input support includes text; support varies by model. Tool-calling support is unspecified for 1 model.

### How do I use NVIDIA models through an API?

Use the exact model identifier from the model page with the Impossibl API. For example, select nvidia/nemotron-3.5-lightning with /v1/chat/completions. Endpoint compatibility depends on the selected model. The API quickstart explains how to create an API key and send a request.

## Sources and related links

Prices, capabilities, limits, and availability describe the public Impossibl API offering. An unpublished fact is unknown; a published zero price is zero. Compare matching billing units and check context tiers before estimating costs.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [Model directory as Markdown](<https://impossibl.com/models.md>)
- [API quickstart](<https://impossibl.com/docs/agent-quickstart>)
- [Model documentation](<https://impossibl.com/docs/models>)