CONCENTRATE

One API for every major LLM provider — routing, spend, logs, and controls in one place.

New York

130 E 59th St, 17th floor

New York, NY 10022

Wilmington

1201 N. Market Street, Suite 200

Wilmington, DE 19801

LLM Gateway
  • LLM Gateway
  • Request Routing
  • Usage Monitoring
  • Spend Management
  • Data Security
  • Access Controls
Teams
  • AI Engineering
  • Engineering Leadership
  • Finance & Operations
  • Security & Compliance
Integrations
  • All Integrations
  • Migration Guides
Platform
  • Pricing
  • Model Fortress
  • Enterprise
  • Documentation
  • Status
Legal
  • Privacy Policy
  • Terms of Service
  • Data Processing Addendum
  • Acceptable Use Policy
Features
  • Universal API Keys
  • Spend Tracking
  • Token Allocation
  • Usage Analytics
  • Request Logs
  • Alerts
  • Data Redaction
  • Zero Data Retention
  • Audit Logs

LLM Gateway

  • LLM Gateway
  • Request Routing
  • Usage Monitoring
  • Spend Management
  • Data Security
  • Access Controls

Teams

  • AI Engineering
  • Engineering Leadership
  • Finance & Operations
  • Security & Compliance

Integrations

  • All Integrations
  • Migration Guides

Platform

  • Pricing
  • Model Fortress
  • Enterprise
  • Documentation
  • Status

Legal

  • Privacy Policy
  • Terms of Service
  • Data Processing Addendum
  • Acceptable Use Policy

Features

  • Universal API Keys
  • Spend Tracking
  • Token Allocation
  • Usage Analytics
  • Request Logs
  • Alerts
  • Data Redaction
  • Zero Data Retention
  • Audit Logs

Offices

New York

130 E 59th St, 17th floor

New York, NY 10022

Wilmington

1201 N. Market Street, Suite 200

Wilmington, DE 19801

© 2026 Concentrate AI. All rights reserved.

CONCENTRATE
Pricing
ModelsDocsRequest a Demo
Back to Model Fortress

Nemotron 3 Ultra NVFP4

NVIDIA
nvidia/nemotron-3-ultra-nvfp4
Released Jun 2, 2026
Chat
Providers
1
Context
262K
Input
$0.60/M
Output
$2.40/M
Aliases:nemotron-3-ultranvidia-nemotron-3-ultra-nvfp4

NVIDIA's frontier-scale hybrid Latent-MoE model (550B total, 55B active) for the most demanding agentic, reasoning, and long-context workloads across code, math, and science. Trained with an NVFP4 recipe.

NVIDIA's frontier-scale hybrid Latent-MoE model (550B total, 55B active) for the most demanding agentic, reasoning, and long-context workloads across code, math, and science. Trained with an NVFP4 recipe.

Fireworks AI

fireworks/nemotron-3-ultra-nvfp4
262K context262K max out
Input Price
$0.60/M tokens
Output Price
$2.40/M tokens
Cache read: $0.12/M
CONCENTRATE
Log In
Log In