Eligible new accounts get $0.10 in free API credit. Once per account; abuse limits apply. Create an account

Outrun

UNCENSORED / TEXT

Nemotron 3 Ultra 550B Uncensored API pricing

$1.69 in / $9.90 out per 1M tokens

Nemotron 3 Ultra 550B Uncensored costs $1.69 per 1M input tokens and $9.90 per 1M output tokens (cached input $0.43). Call it with model ID nemotron-3-ultra-550b-a55b-uncensored at https://api.outrun.to/v1 using one prepaid Outrun key. Prices as of October 30, 2026.

nemotron-3-ultra-550b-a55b-uncensoredOpenAI compatibleUncensoredAudit results

USD / 1M TOKENS

How much does Nemotron 3 Ultra 550B Uncensored cost per 1M tokens?

Get a key ↗

Standard

Token typeOutrun
Input$1.69
Cached input$0.43
Output$9.90

Billed prices, rounded up to the cent. Prices as of October 30, 2026.

Context window
262,144 tokens
Max output
65,536 tokens
Input
Text

What is Nemotron 3 Ultra 550B Uncensored?

Nemotron 3 Ultra 550B Uncensored is a text model in the Outrun catalog. The base model is Nemotron 3 Ultra 550B A55B. The standard rate is $1.69 in / $9.90 out per 1M tokens.

What does uncensored mean?

Uncensored models are tuned or configured to refuse far less than mainstream chat models. Behaviour and quality differ by model, so test the one you choose.

Use of Nemotron 3 Ultra 550B Uncensored is subject to the acceptable use terms in the Outrun Terms of Service.

What are the Nemotron 3 Ultra 550B Uncensored model details?

Model detailValue
DeveloperNVIDIA
Base modelNemotron 3 Ultra 550B A55B
KindText
Parameters550B total / 55B active (base model)
LicenceOpenMDW License Agreement 1.1 (base model)

How do I call Nemotron 3 Ultra 550B Uncensored?

Use your Outrun key and the exact model ID. Requests use prepaid USD credit.

cURL
curl https://api.outrun.to/v1/chat/completions \
  -H "Authorization: Bearer $OUTRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nemotron-3-ultra-550b-a55b-uncensored",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 8192
}'
Python · OpenAI SDK
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.outrun.to/v1",
    api_key=os.environ["OUTRUN_API_KEY"],
)
reply = client.chat.completions.create(
    model="nemotron-3-ultra-550b-a55b-uncensored",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=8192,
)
print(reply.choices[0].message.content)

Which tools work with Nemotron 3 Ultra 550B Uncensored?

Any client that accepts an OpenAI-compatible base URL and a model ID can use nemotron-3-ultra-550b-a55b-uncensored. Setup guides: Roo Code for uncensored models, Cline (OpenAI Compatible), OpenCode, SillyTavern, LiteLLM.

Use these setup values for this model ID. Recommended output settings can be lower than the route maximum.

Set this valueValue
API formatOpenAI compatible
Base URLhttps://api.outrun.to/v1
Model IDnemotron-3-ultra-550b-a55b-uncensored
Context window262,144
Max output setting8,192
Temperature1
StreamingYes
Image supportNo
R1 formatNo
Include max tokensYes
Reasoning overrideNo
Prompt caching settingNo
CapabilitySupported
Tool callingYes
StreamingYes
Image inputNo
Roo Code readyYes

How does Nemotron 3 Ultra 550B Uncensored compare on cost?

ModelInput / output1,000 chat turns
GLM-5.3 Flash Uncensored$0.05 / $0.05$0.07
glm-5.3-flash-uncensored-2Route 2$0.17 / $0.17$0.22
glm-5.3-flash-uncensored-3Route 3$0.40 / $1.60$0.88
GLM-5.3 Uncensored$0.10 / $0.10$0.13
glm-5.3-uncensored-2Route 2$0.35 / $0.35$0.46
glm-5.3-uncensored-3Route 3$2.50 / $4.50$3.85
GLM-5.3 Flash Apex Abliterated$0.30 / $1.00$0.60
DeepSeek V4 Pro Uncensored$0.50 / $0.50$0.65
GPT OSS 120B Uncensored$0.22 / $1.46$0.66
DeepSeek V4.1 Flash Uncensored 1017$0.66 / $2.64$1.46
DeepSeek V4.1 Flash Uncensored Thinking 1017$0.66 / $2.64$1.46
GLM-5.3 Flash Abliterated$1.32 / $1.32$1.72
DeepSeek V4.1 Flash Abliterated Fast$1.40 / $1.40$1.82
GLM-5.3 Abliterated$1.40 / $1.40$1.82
glm-5.3-abliterated-2Route 2$4.50 / $4.50$5.85
MiMo V2.6 Flash Abliterated$1.00 / $3.00$1.90
MiMo V2.6 Flash Uncensored$1.00 / $3.00$1.90
MiMo V2.6 Flash Uncensored Thinking$1.00 / $3.00$1.90
DeepSeek V4.1 Flash Abliterated$2.10 / $2.10$2.73
deepseek-v4.1-flash-abliterated-2Route 2$0.30 / $0.30$0.39
MiniMax M3 Uncensored$1.50 / $8.00$3.90
Hermes 4 405B Uncensored$1.80 / $7.20$3.96
Nemotron 3 Ultra 550B UncensoredThis model$1.69 / $9.90$4.66
GLM-5.3 Flash Code Uncensored$12.00 / $12.00$15.60

Assumes 1,000 input + 300 output tokens per turn, repeated 1,000 times, at standard-tier rates without caching. Input / output shown per 1M tokens, rounded up to the cent.

Common questions about Nemotron 3 Ultra 550B Uncensored

How much does the Nemotron 3 Ultra 550B Uncensored API cost?

Nemotron 3 Ultra 550B Uncensored costs $1.69 per 1M input tokens and $9.90 per 1M output tokens (cached input $0.43). Prices as of October 30, 2026.

What model ID and base URL do I use for Nemotron 3 Ultra 550B Uncensored?

Use the model ID nemotron-3-ultra-550b-a55b-uncensored with the base URL https://api.outrun.to/v1 and your Outrun API key.

Does Nemotron 3 Ultra 550B Uncensored accept images?

No. Nemotron 3 Ultra 550B Uncensored takes text input only.

Does Outrun store my prompts when I use Nemotron 3 Ultra 550B Uncensored?

Outrun does not store your prompts, images or outputs unless you choose to save them.