agentmods.dev

cuopt-server-api-python

A guide for running NVIDIA cuOpt as a web service and calling it with Python, curl, or another language. cuOpt solves routing, linear-programming, and mixed-integer linear-programming problems; it does not support quadratic programming through this service.

In plain words
What is it for?
Use it to run cuOpt locally, in Docker, Kubernetes, or the cloud, and to send supported optimization problems to its REST endpoints.
Why use it?
It helps connect an application to cuOpt without guessing how to deploy the server or format HTTP requests. It also helps diagnose rejected request data.

Skill for Claude CodeCodex

1.0k 3d ago A scan 34 tokens copy · 100% Apache-2.0
View the source file NVIDIA/cuopt
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nvidia/cuopt/cuopt-server-api-python
Any agent
npx skills add NVIDIA/cuopt --skill cuopt-server-api-python
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/cuopt

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,590 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.01590
Opus 5 $0.00017 $0.00795
Sonnet 5 $0.00007 $0.00318
Haiku 4.5 $0.00003 $0.00159

Measured yesterday against content hash a663a623aa38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cuopt-server-api-python scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

The scan reads SKILL.md. This mod also ships 5 executable files (assets/lp_basic/client.py, assets/milp_basic/client.py, assets/pdp_basic/client.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: cuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.
Origin

This is a copy

100% identical to cuopt-server-api-python — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/cuopt-server-api-python/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cuOpt Server — Deploy and client (Python/curl)

This skill covers starting the server and client examples (curl, Python). Server has no separate C API (clients can be any language).

Purpose

Use this skill when the user is deploying the cuOpt REST server or writing a client against it — choosing a deployment target, mapping a problem onto the HTTP endpoints, translating between Python-API and REST field names, or debugging a rejected payload.

Prerequisites

  • An NVIDIA GPU with a working CUDA driver (the server requires one; --gpus all for Docker).
  • cuopt-server installed, or Docker with the NVIDIA Container Toolkit. See the install skill.
  • Python clients need requests. No API key or auth token is required by the server itself.

Problem types supported

Problem type Supported
Routing ✓
LP ✓
MILP ✓
QP ✗

Required questions

Ask these if not already clear:

  1. Problem type — Routing or LP/MILP? (QP not available via REST.)
  2. Deployment — Local, Docker, Kubernetes, or cloud?
  3. Client — Which language or tool will call the API (e.g. Python, curl, another service)?

Start server

# Development
python -m cuopt_server.cuopt_service --ip 0.0.0.0 --port 8000

# Docker — pick the tag matching your CUDA major version
docker run --gpus all -d -p 8000:8000 -e CUOPT_SERVER_PORT=8000 \
  nvidia/cuopt:latest-cu13

Use latest-cu12 or latest-cu13 to match your driver's CUDA major version (latest-cu13-ubi10 for a UBI10 base). Prefer these over the CUDA+Python-specific tags such as latest-cuda12.9-py3.13 — those track a single Python line and go stale when it stops receiving builds.

For production, pin rather than float: latest-* tags are mutable and can silently move to a different image. Use a full release tag (nvidia/cuopt:<release>-cuda<cuda>-py<python>) or an immutable digest (nvidia/cuopt@sha256:<digest>). Check the nvidia/cuopt registry for available tags.

Read the full file on GitHub · 138 lines

Files

What ships with it

15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 138 lines · 34 tokens per session scan A a663a623aa38

Subscribe to this mod's changes

cuopt-server-api-python is a skill published in the GitHub repository NVIDIA/cuopt (1,032 stars, last pushed 3d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,590 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to cuopt-server-api-python, differing in 0 lines, and is treated as a copy.

Backend and APIsDevOps and cloudGPULanguagesOptimizationcudalinear-programming
Related

Other skills, from other repositories

add-cuda-kernel

Step-by-step tutorial for adding new CUDA kernels to FlashInfer.

flashinfer-ai/flashinfer · 18 tokens

debug-cuda-crash

Tutorial for debugging CUDA crashes using API logging.

flashinfer-ai/flashinfer · 14 tokens

benchmark-kernel

Guide for benchmarking FlashInfer kernels with CUPTI timing.

flashinfer-ai/flashinfer · 14 tokens

cutedsl_megamoe

Skill "cutedsl_megamoe" from flashinfer-ai/flashinfer, covering updating the cutedsl megamoe kernel src, layout, when the kernel team drops a new version of src/ and what not to update here.

flashinfer-ai/flashinfer · 0 tokens

perf-torch-cuda-graphs

Apply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch makegraphedcallables, TE makegraphedcallables, MCore CudaGraphManager, FullCudaGraphWrapper, manual torch.cuda.graph), code compatibility, capture workflows, dynamic pattern handling, and troubleshooting. Triggers: CUDA graph…

NVIDIA/TensorRT-LLM · 119 tokens

perf-optimization-casebook

Casebook of past successful and classic TensorRT-LLM optimizations (runtime/execution and kernel level) recorded as reusable decision precedents. Consult when deciding which optimization to apply for a classified bottleneck or a given config/model/hardware, to find prior art and adapt a proven approach instead of…

NVIDIA/TensorRT-LLM · 91 tokens