LLM Reference
NVIDIA NIM

NVIDIA NIM

Researched 6d agoInference PlatformTier 2

NVIDIA

CodingRAGAgentsLong contextVisionClassificationJSON / Tool useHighlightHyperscaler

NVIDIA NIM offers 143 tracked models (1 with output token pricing). This catalog covers coding, rag, and agents; open any model detail page for benchmarks, batch tiers, and migration prompts.

Covers 7 workload areas across 143 tracked models; last verified 2026-06-30.

Use it for

  • Teams comparing token and batch pricing across this provider's models
  • Operators routing coding, rag, and agents workloads through this API

Do not use it for

  • Final benchmark picks without opening the relevant model detail page

Tracked models

143

Models available through this provider

Priced output routes

1

Models with output token pricing tracked

Cheapest output

$0.500

Nemotron 3 Super-120B-A12B on this route

Batch-ready models

0

No batch pricing tracked

Latest model release

2026-05-31

36d since newest release

Freshness

2026-06-30

Researched 6d ago

fresh

Routes available via routers & gateways

These routers list NVIDIA NIM as a target provider, so they can sit in front of this catalog for fallback, routing, or unified API access.

Browse routers ->

Information

TypeInference Platform
TierTier 2
Models143
CompanyNVIDIA
Founded1993
Santa Clara, California, United States

NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices. Developers can try hosted NIM APIs through the NVIDIA API Catalog on build.nvidia.com, then move the same model families into self-hosted NIM containers on NVIDIA GPUs in a data center, private cloud, public cloud, or workstation. The catalog positions NIM around optimized open and NVIDIA models, including chat, coding, reasoning, retrieval, vision, speech, and safety use cases, with downloadable model cards and API endpoints where NVIDIA exposes them.

Catalog freshness

The newest model tracked on this provider was released 2026-05-31 (36d ago).

Where this host wins

  • Coding: 33 tracked models with SWE-bench / HumanEval-style scores.
  • RAG: 36 tracked models with ruler / needle retrieval benchmarks.
  • Agentic: 21 tracked models with BFCL, tau-bench, and SWE-bench tool-use coverage.
  • Long-context: 61 tracked models with context-token or InfiniteBench-class signal.

Getting started

Official product, docs, and pricing links — confirm quotas and regions in the vendor docs.

Compliance notes

No verified compliance claims (SOC 2, ISO, HIPAA) tracked for this provider yet — check the vendor's trust center for current certifications.

Platform Overview

NIM packages inference runtimes and model profiles into containers that expose standard API surfaces such as chat completions, completions, model listing, tokenization, health, and management endpoints. The hosted API path is useful for prototyping and catalog discovery, while the NGC/container path is the self-hosted route for teams that want GPU-hour infrastructure control, private-network deployment, Kubernetes scaling, or NVIDIA AI Enterprise support. Per-token pricing is not a universal provider-level claim in the current seed data; pricing should stay attached to sourced model-provider rows or NVIDIA's current catalog terms.

Compare per-model pricing, input and output token costs, batch availability, and benchmark coverage.

For Moonshot's catalog model, see Kimi K2.6 on NVIDIA NIM or the NVIDIA NIM deployment guide for Kimi K2.6 (moonshotai/kimi-k2.6). The full Kimi K2.6 reference includes benchmarks and all providers.

Available Models(143)

View all →
ModelInput (per 1M)Output (per 1M)Type
Cosmos 3 Nano
Provisioned
Cosmos 3 Super
Provisioned
Step 3.7 Flash
Provisioned
Kimi K2.6
Serverless
Mistral Small 4
Serverless
Kimi K2.5
Serverless
Nemotron 3 Super-120B-A12B$0.10$0.50
Serverless
GLM-5
Serverless
Mistral Small 3.1 24B Instruct
Serverless
Nemotron 3 Nano
Serverless
View full catalog →

Where else to run this