NVIDIA NIM
Researched 1d agoInference PlatformTier 2NVIDIA
NVIDIA NIM exposes 140 tracked models (0 with output token pricing in seed data). Task coverage across this catalog includes coding, rag, and agents; open any model detail page for benchmarks, batch tiers, and migration prompts.
Portfolio context: 7 decision-task tags, 140 catalog rows, latest research stamp 2026-05-22.
Use this portfolio page for
- Operators routing coding, rag, and agents workloads through this API
Do not stop here for
- Final benchmark picks without opening the relevant model detail page
- Strict price-per-token comparisons until output pricing is sourced
Catalog rows
140
Models linked to this provider in seed data
Priced output routes
0
Add output pricing to unlock comparisons
Cheapest output
Unknown
Need positive token_out rows
Batch-ready SKUs
0
No batch pricing tracked
Latest catalog ship
2026-04-20
33d since dated release field
Freshness
2026-05-22
Researched 1d ago
Catalog release signal
Latest ISO-dated model.release in this catalog is 2026-04-20 (33d ago).
Where this host wins
- Coding: 29 tracked models with SWE-bench / HumanEval-style scores.
- RAG: 35 tracked models with ruler / needle retrieval benchmarks.
- Agentic: 19 tracked models with BFCL, tau-bench, and SWE-bench tool-use coverage.
- Long-context: 58 tracked models with context-token or InfiniteBench-class signal.
Getting started
Official entry points from seed metadata — confirm quotas and regions in vendor docs.
Compliance notes (verbatim seed excerpts)
Not yet verified from seed copy — no SOC/ISO/HIPAA-class sentences detected to quote verbatim.
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.
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(140)
View all →| Model | $/GPU·hr | GPU Config | Type |
|---|---|---|---|
| Kimi K2.6 | $1.00 | — | Serverless |
| Mistral Small 4 | $1.00 | 1xH100 | Serverless |
| Kimi K2.5 | $1.00 | — | Serverless |
| Nemotron 3 Super-120B-A12B | $1.00 | 1xH100 | Serverless |
| GLM-5 | $1.00 | — | Serverless |
| Mistral Small 3.1 24B Instruct | $1.00 | — | Serverless |
| Nemotron 3 Nano | $1.00 | 1xH100 | Serverless |
| DeepSeek V3.2 | $1.00 | 1xH100 | Serverless |
| Mistral Large 3 675B Instruct | $1.00 | 4xH100 | Serverless |
| Mistral Nemotron | $1.00 | — | Serverless |
Platform Details
Organization
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.