browse by creator
NVIDIA
NVIDIA API and models: 2 models on Impossibl, including Nemotron 3.5 Lightning and Nemotron 3 Ultra 550B A55B. Compare pricing per million tokens, context windows, and capabilities between different NVIDIA models.
models
2
modalities · in → out
takes text in, gives text out
latest release
Nemotron 3.5 LightningAug 11, 2026
- Nemotron 3.5 Lightning
nvidia/nemotron-3.5-lightning
Nemotron 3.5 Lightning is NVIDIA's open mixture-of-experts model, the efficiency-focused member of the Nemotron 3 family, built for high-throughput, always-on agentic workloads.
NVIDIAText generation
- context
- 262.14ktokens
- input price
- $0.05/1m tokens
- output price
- $0.20/1m tokens
- released
- Nemotron 3 Ultra 550B A55B
nvidia/nemotron-3-ultra-550b-a55b
Nemotron 3 Ultra is NVIDIA's open-weight language model for reasoning, coding, and coordinating tasks through tools.
NVIDIAText generation
- context
- 262.14ktokens
- input price
- $0.60/1m tokens
- output price
- $2.40/1m tokens
- released
- —
compare NVIDIA models
compare models with the same model type and billing unit. each comparison includes published api prices, context limits, and capabilities.
frequently asked questions
Which Nemotron models are available through Impossibl?
The directory lists 2 models from NVIDIA available through the Impossibl API, including Nemotron 3.5 Lightning and Nemotron 3 Ultra 550B A55B. Open each model page for its API identifier, capabilities, and current pricing.
How much do Nemotron 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 is the cheapest Nemotron model?
By published input rate, the cheapest Nemotron text generation model on Impossibl is Nemotron 3.5 Lightning (nvidia/nemotron-3.5-lightning) at $0.05 per million input tokens and $0.20 per million output tokens. Cheapest by input rate is not always cheapest for a workload; output-heavy or cached requests can favor another model.
Does Impossibl add a markup to NVIDIA pricing?
No. Usage is charged at the provider's list price with 0% usage markup. Prepaid credit purchases include a 5% platform fee, and there is no subscription. The rates on this page are NVIDIA's published base rates, and usage comes off your balance when the request finishes.
What context windows do Nemotron models support?
Among NVIDIA models with a published limit on Impossibl, the largest context window is 262,144 tokens, listed for Nemotron 3 Ultra 550B A55B and Nemotron 3.5 Lightning. Context limits vary by model and are separate from maximum output limits.
What inputs and capabilities do Nemotron models support?
Available model types include text generation. Published input support includes text; support varies by model. Tool-calling support is unspecified for 2 models.
How do I use Nemotron 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.