NVIDIA's open-weight model optimized for reasoning, coding, and long-context text generation. Engineers should use it when they need a balance of throughput and frontier-level performance without proprietary API constraints.
Modalities
Text → Text
Input
$0.675 /1M
Output
$3.375 /1M
Cached input
$0.0675 /1M90% off
Context
1M
Speed
fast
Performance
Live production data from real requests on Kyma — not synthetic benchmarks.
Rank
#32
of 87 active models
Tokens served
464.1K
all-time
Success rate
100%
last 7 days
Pricing
Pay per token. Cached input is billed at 10% of the input rate.
+ Estimate your workload− Estimate your workload
Estimated monthly cost
$80.19
$2.67 / day on Nemotron 3 Ultra 550B
Same workload on:
Estimates use list pricing with cached input billed at the 90%-discount rate. Actual bills depend on real token counts — every response includes its exact cost.
When to use Nemotron 3 Ultra 550B
Where this model earns its cost — and where it doesn't.
Nemotron 3 Ultra 550B is a 550B parameter mixture-of-experts architecture with 55B active parameters per forward pass. It combines a hybrid Mamba-Transformer design to handle reasoning, coding, and general-purpose text tasks efficiently.
On Kyma, the model runs through an OpenAI-compatible endpoint with automatic request failover and exact cost reporting in the response payload. It supports tool use, structured outputs, and prompt caching, which bills repeated prefixes at 10% of the standard input rate.
The model accepts a 1,000,000 token context window but caps generation at 32,768 output tokens. It is strictly text-only and does not support vision or multimodal inputs.
Long Context Document Analysis
Process large technical manuals or codebases within the one million token window.
Automated Code Generation
Generate and refactor code using built-in reasoning and tool-use capabilities.
High Throughput Chat
Handle conversational workloads that require fast text generation and structured JSON outputs.
Reasoning Heavy Workflows
Execute multi-step logical tasks where active parameter routing improves accuracy.
Not ideal for: Tasks requiring image or video understanding, or workloads that need output sequences longer than 32,768 tokens.
How it compares
Against the peers people actually weigh it against.
| Spec | Nemotron 3 Ultra 550B | Muse Spark 1.1 | Grok 4.5 |
|---|---|---|---|
| Input /1M | $0.675 | $1.688 | $2.70 |
| Output /1M | $3.375 | $5.738 | $8.10 |
| Context | 1M | 1M | 500K |
| Tools | Yes | Yes | Yes |
| Reasoning | Yes | Yes | Yes |
| Speed | fast | medium | medium |
Quick start
Up and running in under two minutes.
- 1
Create an API key
Sign up and grab a key from the dashboard — $0.50 free credit, no card required.
Get API key → - 2
Make your first request
Drop in your key and send a chat completion — fully OpenAI-compatible.
curl https://kymaapi.com/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "nemotron-3-ultra-550b", "messages": [ {"role": "user", "content": "Explain prompt caching in one paragraph."} ] }' - 3
Stream responses
Add
"stream": trueto receive tokens as they arrive.curl https://kymaapi.com/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "nemotron-3-ultra-550b", "stream": true, "messages": [{"role": "user", "content": "Hello!"}] }'
FAQ
Common questions about this model.