inference

A command-line interface for Scaleway’s inference service, which runs machine-learning models so applications can use their results.

In plain words
What is it for?
Use it to create an inference deployment, choose its model and compute node, accept its license, add tags, and configure public endpoints.
Why use it?
It provides commands for creating and managing dedicated model-serving deployments instead of configuring them manually.

Command

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 commands/scaleway/scaleway-cli/inference
Clone the repo
git clone --depth 1 https://github.com/scaleway/scaleway-cli
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,419 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% 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 $0.00000 $0.02419
Opus 5 $0.00000 $0.01210
Sonnet 5 $0.00000 $0.00484
Haiku 4.5 $0.00000 $0.00242

Measured 2d ago against content hash 7645427ff41f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

inference scanned grade A with 0 findings 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 2d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

86% identical to datawarehouse — 322 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.

docs/commands/inference.md · 351 lines

How it starts

The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation for scw inference

This API allows you to handle your Generative APIs - Dedicated Deployment services.

Deployment commands

Deployment commands.

Create a deployment

Create a new inference deployment related to a specific model.

Usage:

scw inference deployment create [arg=value ...]

Arguments:

Name Description Argument Specifications
name Name of the deployment RequiredDefault: <generated>
project-id Project ID to use. If none is passed the default project ID will be used
model-id ID of the model to use Required
accept-eula Accept the model's End User License Agreement (EULA).
node-type-name Name of the node type to use Required
tags.{index} List of tags to apply to the deployment
min-size Defines the minimum size of the pool
max-size Defines the maximum size of the pool. Currently, autoscaling is not yet supported, and this value must be equal to min_size
endpoints.{index}.public-network Set the endpoint as public
endpoints.{index}.is-public Will configure your public endpoint if true Default: true
endpoints.{index}.private-network.private-network-id
endpoints.{index}.disable-auth Disable the authentication on the endpoint. Default: false
quantization.bits The number of bits each model parameter should be quantized to. The quantization method is chosen based on this value.
region Region to target. If none is passed will use default region from the config Default: fr-parOne of: fr-par

Read the full file on GitHub · 351 lines

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. 2d ago First seen · 351 lines · 0 tokens per session scan A 7645427ff41f

Subscribe to this mod's changes

inference is a command published in the GitHub repository scaleway/scaleway-cli (996 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,419 tokens. A static security scan graded it A with 0 findings. It is 86% identical to datawarehouse, differing in 322 lines, and is treated as a copy.