NVIDIA cuOpt is an optimization engine that uses GPUs to solve mathematical planning problems such as linear programming, quadratic programming, and vehicle routing. Developers and operations teams use its C++, C, Python, and server APIs for large-scale optimization, while the catalogue's agent skills connect it with agent-based optimization workflows.
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.
npx skills add NVIDIA/cuopt --skill cuopt-server-api-pythongit clone --depth 1 https://github.com/NVIDIA/cuoptWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nvidia/cuopt/cuopt-server-api-python)<a href="https://agentmods.dev/skills/nvidia/cuopt/cuopt-server-api-python"><img src="https://agentmods.dev/badge/skills/nvidia/cuopt/cuopt-server-api-python/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nvidia/cuopt/cuopt-server-api-python"><img src="https://agentmods.dev/badge/skills/nvidia/cuopt/cuopt-server-api-python.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.01575 |
| Opus 5.5 | $0.00014 | $0.00630 |
| Sonnet 5.5 | $0.00007 | $0.00315 |
| Haiku 4.5 | $0.00003 | $0.00158 |
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 9d ago.
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. 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.
How it starts
The opening of the file, as written. The whole thing — 137 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 allfor Docker). cuopt-serverinstalled, 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:
- Problem type — Routing or LP/MILP? (QP not available via REST.)
- Deployment — Local, Docker, Kubernetes, or cloud?
- 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).
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>-cu<cuda-major>) or an immutable digest (nvidia/cuopt@sha256:<digest>). Check the nvidia/cuopt registry for available tags.
Verify
Confirm the server is up by requesting GET /cuopt/health on the local port (e.g. http://localhost:8000/cuopt/health) — a healthy server returns HTTP 200.
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.
- assets/lp_basic/client.py 2.9 KB runs code
- assets/lp_basic/README.md 368 B
- assets/milp_basic/client.py 2.8 KB runs code
- assets/milp_basic/README.md 360 B
- assets/pdp_basic/client.py 3.3 KB runs code
- assets/pdp_basic/README.md 287 B
- assets/README.md 608 B
- assets/vrp_basic/client.py 3.5 KB runs code
- assets/vrp_basic/README.md 376 B
- assets/vrp_simple/client.py 3.2 KB runs code
- assets/vrp_simple/README.md 254 B
- BENCHMARK.md 8.8 KB
- evals/evals.json 8.5 KB
- skill-card.md 4.2 KB
- skill.oms.sig 7.0 KB
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.
- 9d ago Changed 272d2f7f0f6a
- 11d ago Changed 47e4ddd59c14
- 1mo ago Changed f82d7dadb963
- 1mo ago Changed · -1 lines f8e388002685
- 1mo ago First seen · 138 lines · 34 tokens per session scan A a663a623aa38
cuopt-server-api-python is a skill published in the GitHub repository NVIDIA/cuopt (1,075 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 1,575 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
dstack-prototyping
Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final…
next_cutedsl_megamoe
Use the reconciled source and exporter revisions recorded in VENDOR.md. Select both Blackwell inference entry points and retain their runtime dependency closure. Regenerate the complete src/sources/ tree, then compare every file against a second export. Do not combine independently pinned helper snapshots or modify…
perf-optimize
Launch and operate this repo's perf-optimize workflow, which iteratively APPLIES TensorRT-LLM serving optimizations — baseline benchmark at one concurrency or a Pareto curve of them (tok/s/user vs tok/s/gpu), analytical SOL projection on by default (via the internal-perf-sol-analysis skill) sizing the headroom the…
cutedsl_megamoe
The explicit GenPhase prototype is independently owned by ../nextcutedslmegamoe. This legacy package lazily re-exports its six public GenPhase names. Follow that package's update workflow for GenPhase changes; keep this older snapshot separate. The default backend heuristics do not select GenPhase automatically.
pull_style_cutedsl_megakernel
This tree vendors the kernel team's SM90 FP8 MegaMoE drop — a fork of the same kernel repo that kernelsrc/sm100/cutedslmegamoe vendors (Bangyu's SM100 tree). The SM90 work (Vincent's hoppermegamoe branch) moved the shared runtime forward, so this tree duplicates common/, src/, and moenvfp4swapab/ at its own revision…
swapab_cutedsl_megakernel
Skill "swapab_cutedsl_megakernel" from flashinfer-ai/flashinfer, covering updating the sm120 swap-ab cutedsl megamoe kernel src, layout, when the kernel team drops a new version of src/ and what not to update here.