Nemotron 3 Ultra

tools

nemotron-3-ultraNVIDIA's open frontier reasoning and orchestration model (550B MoE).

Try in playground

Input / 1M tokens

$0.5

$0.0000005 / token

Output / 1M tokens

$2.2

$0.0000022 / token

Cached input / 1M

$0.1

Uptime · 24h

—

No traffic yet

Details

Type: Chat
Input: text
Output: text
Context: 262,144 tokens

Supported parameters

max_tokenstemperaturetop_pstopseedpresence_penaltyfrequency_penaltyresponse_formatpluginstoolstool_choiceparallel_tool_calls

Last 24 hours

Requests per hour; red = provider errors.

Avg latency: —
Avg first token: —
Throughput: —

Use it

curl https://api.ultragpt.pro/v1/chat/completions \
  -H "Authorization: Bearer $ULTRAGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nemotron-3-ultra",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Anthropic SDK / Claude Code

curl https://api.ultragpt.pro/v1/messages \
  -H "x-api-key: $ULTRAGPT_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nemotron-3-ultra",
    "max_tokens": 1024,
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'