Models / Uncensored / NVIDIA
Nemotron 3 Ultra 550B Uncensored API pricing
$1.125 in, $6.60 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | NVIDIA list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $1.125 | — |
| Cached input | — | $0.282 | — |
| Output | — | $6.60 | — |
Nemotron 3 Ultra 550B Uncensored specs
- Context window
- 262,144 tokens
- Max output
- 65,536 tokens
- Input
- text
Nemotron 3 Ultra 550B Uncensored: Nemotron 3 Ultra served without a filter · the official model, changed to answer
Nemotron 3 Ultra 550B Uncensored is NVIDIA's Nemotron 3 Ultra served without a content filter: the official model, changed to answer instead of refuse by a method its name does not state. Nemotron 3 Ultra is NVIDIA’s largest open model: a 550B-parameter mixture of experts with about 55B active per token. It is served as nemotron-3-ultra-550b-a55b-uncensored at $1.125 input and $6.60 output per million tokens, one of 146 builds in the uncensored LLM API, on the same key as every other model. Added 2026-10-21.
| Nemotron 3 Ultra 550B Uncensored | |
|---|---|
| Developer | NVIDIA |
| Based on | Nemotron 3 Ultra 550B |
| Kind | the official model, served without a content filter |
| Context window here | 262,144 tokens |
| Max output | 65,536 tokens |
| Input | text |
| Added | 2026-10-21 |
From the live catalog, read 2026-10-21.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"nemotron-3-ultra-550b-a55b-uncensored","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'What uncensored means for Nemotron 3 Ultra 550B Uncensored · the daily real-model check is the live evidence
Uncensored here means the model answers what a filtered build of the same weights declines. Nothing is added to your prompt, and the id names the method only as far as "uncensored". The filtered Nemotron 3 Ultra 550B runs on the same key at $1.50 / $1.50 per million tokens, so a tool switches between the two by model id.
The daily real-model check is the live evidence: it confirms the model answering nemotron-3-ultra-550b-a55b-uncensored is the one we serve, checked every day.
Nemotron 3 Ultra 550B Uncensored next to the other uncensored models · per million tokens, live
A chat turn is 2,000 input and 500 output tokens. Live from the catalog, ordered by the cost of 1,000 turns.
Worked for Nemotron 3 Ultra 550B Uncensored: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $1.125 input and $6.60 output per million tokens, that is $2.25 + $3.30 = $5.55, paid from prepaid credit with no subscription.
Nemotron 3 Ultra 550B Uncensored API · base URL and key
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="nemotron-3-ultra-550b-a55b-uncensored",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.uplinkswitch.com/v1',
apiKey: 'sk-uplink-live-...',
});
const completion = await client.chat.completions.create({
model: 'nemotron-3-ultra-550b-a55b-uncensored',
messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"nemotron-3-ultra-550b-a55b-uncensored","messages":[{"role":"user","content":"Hello"}]}'What would it cost? · paste a prompt, priced before you send it
Input is counted at about 4 characters per token.
Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.
More from NVIDIA
Nemotron 3 Ultra 550B Uncensored questions
- What is Nemotron 3 Ultra 550B Uncensored?
- Nemotron 3 Ultra 550B Uncensored is a model from NVIDIA, with a 262,144-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as nemotron-3-ultra-550b-a55b-uncensored.
- How much does the Nemotron 3 Ultra 550B Uncensored API cost?
- $1.125 per million input tokens and $6.60 per million output tokens, with cached input at $0.282.
- Is Nemotron 3 Ultra 550B Uncensored free?
- It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.0044.
- What is the Nemotron 3 Ultra 550B Uncensored context window?
- Nemotron 3 Ultra 550B Uncensored has a 262,144-token context window, with up to 65,536 output tokens per request. It takes text input.
- What is the Nemotron 3 Ultra 550B Uncensored model id?
- nemotron-3-ultra-550b-a55b-uncensored. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Nemotron 3 Ultra 550B Uncensored API key?
- Create one in the console at uplinkswitch.ai/console: prepaid credit from $10, no subscription, and the key is live at once. The same key calls Nemotron 3 Ultra 550B Uncensored and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is it the real Nemotron 3 Ultra 550B Uncensored?
- Every day each model gets the same test prompt, and a model always counts that prompt the same way; a swapped one would not. Nemotron 3 Ultra 550B Uncensored's latest result: Same fingerprint since Oct 21, no answer since Oct 22.
- Is there an uncensored Nemotron 3 Ultra API?
- Yes: nemotron-3-ultra-550b-a55b-uncensored on the OpenAI format at https://api.uplinkswitch.com/v1, $1.125 input and $6.60 output per million tokens. The official Nemotron 3 Ultra served without a content filter; no weights to download and no GPU of your own.
- How is Nemotron 3 Ultra 550B Uncensored different from Nemotron 3 Ultra 550B?
- Same model, no filter. Nemotron 3 Ultra 550B (nemotron-3-ultra-550b-a55b) is the filtered build at $1.50 / $1.50 per million tokens; Nemotron 3 Ultra 550B Uncensored is $1.125 / $6.60. Both answer the same base URL and key.
- Is Nemotron 3 Ultra 550B Uncensored really uncensored?
- Nemotron 3 Ultra 550B Uncensored is one of our own models, served live on the OpenAI-compatible API at the same base URL and key as every other model, and it answers the prompts a filtered model declines. The daily real-model check at /proof confirms the model answering nemotron-3-ultra-550b-a55b-uncensored is the live one.
- What does Nemotron 3 Ultra 550B Uncensored cost per 100 messages?
- $0.555 for 100 chat turns of 2,000 input and 500 output tokens each, at $1.125 input and $6.60 output per million tokens, from prepaid credit with no subscription.