Vai al contenuto principale

NVIDIAAdded Jun 4, 2026PrivateOpen weights

NVIDIA Nemotron 3 Ultra

NVIDIA Nemotron 3 Ultra is built for frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads.

nvidia-nemotron-3-ultra-550b-a55bPOST https://api.venice.ai/api/v1/chat/completions
Input / output
$0.625 / $3.13
per 1M tokens
Context
256K
32K max output
Reasoning
none, low, medium, high
default low
Cached input
$0.1875
70% off input
Modalities
Text
out: text

Pricing

USD per 1M tokens
Input
$0.625
Cached input
$0.1875
Output incl. reasoning
$3.13
Similar modelsInputOutputOutput price, relative
NVIDIA Nemotron 3 Ultra$0.625$3.13
Grok Build 0.1$1.00$2.00
Seed 2.1 Turbo$0.625$3.13
Kimi K2.7 Code$0.75$3.50
Aion 3.0 Mini$0.875$1.75

Prompt caching is automatic; see Prompt caching.

Specs

Model ID
nvidia-nemotron-3-ultra-550b-a55b
Endpoint
POST /api/v1/chat/completions
Context window
256,000 tokens
Max output
32,768 tokens
Reasoning effort
reasoning_effort: none | low | medium | high · default low · guide
Served precision
FP8
Added
Jun 4, 2026
Weights
Open

Capabilities

Modalities
Text
Input and output
Image
Not supported
Audio
Not supported
Video
Not supported
Features
Streaming (SSE)
Supported
Function calling
Supported
Structured output (json_schema)
Supported
Reasoning effort
none, low, medium, high
Prompt caching
Supported
Web search
venice_parameters
X search
Not supported
Log probabilities
Not supported
Fine-tuning
Not supported
Image generation
Not supported
POST/api/v1/chat/completionsRecommended
curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia-nemotron-3-ultra-550b-a55b",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "low"
}'

Privacy

Tier 1
Anonymized

Included

Tier 2 · this model
Private

Zero data retention, enforced by contract. Prompts and outputs aren’t stored.

Tier 3
TEE

Not available

Tier 4
End-to-end encrypted

Not available