English Français العربية

ModelSpec

Registre officiel Productivité

Find AI models that fit a job from your requirements, sourced benchmarks and real cost.

Code source Site web Documentation

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

Remote (streamable-http)
Claude Code 
claude mcp add --transport http modelspec 'https://api.modelspec.dev/mcp' --header 'Authorization: <Required ModelSpec bearer API key. Get a key at https://modelspec.dev/pricing/.>'
Configuration JSON (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "modelspec": {
            "type": "http",
            "url": "https://api.modelspec.dev/mcp",
            "headers": {
                "Authorization": "<Required ModelSpec bearer API key. Get a key at https://modelspec.dev/pricing/.>"
            }
        }
    }
}

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. Use ModelSpec
  2. Serving path
  3. Contribute
  4. License

ModelSpec is an analysis of alternatives for AI models: it decides which models fit a job from your requirements, sourced benchmarks and real cost, and shows its work. It reads a spec, filters models and offerings against its constraints, and explains the decision from a versioned snapshot. The catalogue starts as YAML and Markdown, then exports to JSON on Cloudflare Pages (modelspec.dev). No database is on the serving path.

Use ModelSpec

Use the free, rate-limited decision board. Machines have three ways in: the keyed CLI, the remote MCP Worker, and the HTTP API. Decisions require a ModelSpec API key. No data download and no local decision cache.

uvx --from modelspec-dev modelspec       # run without installing
pipx install modelspec-dev
pip install modelspec-dev

pip install modelspec is an unrelated project. Use modelspec-dev. Version 0.2.0 was yanked. 1.0.0 is the thin keyed client. It keeps modelspec compare. decide sends the bounded row list when the Spec omits fields.

Run modelspec or modelspec help agent --json for orientation, modelspec key for prices and access, and modelspec auth set to store a key in a 0600 file under your user config directory. MODELSPEC_API_KEY wins. Then use modelspec decide --spec FILE|- or modelspec decide --template ID. modelspec setup mcp --client claude-desktop prints a client configuration; --write shows a diff and needs confirmation or --yes.

The CLI sends no telemetry and reads no provider API keys. Every error supplies next steps. See the agent guide, OpenAPI, pricing and keys, decision contract, and CLI contract.

Serving path

models/*.md ──▶ pipeline/build.py ──▶ static JSON on Cloudflare Pages
                                      (modelspec.dev /api/*.json)
                                            │
Hosted API ──────────────────────────────────┘

FalkorDB is optional local graph exploration only. It is not required to rank, fit, or render the sites.

Contribute

Read CONTRIBUTING.md. Sign off commits (git commit -s) to certify the DCO — not a copyright assignment. Every fact carries a source and the date it was read; unknown means an empty field.

Cards live in models/{provider}/{model-slug}.md. Edit and open a PR.

License

Two licences, because the code and the corpus want different things.

PartLicence
Code (everything outside the data directories)MIT
Data (models/, benchmarks/, hardware/, hosts/)CC BY-SA 4.0

The corpus is share-alike: build on it, including commercially, but if you redistribute it or a derivative, credit ModelSpec and publish yours under the same terms. The CLI source remains MIT-licensed. Full text in LICENSE and LICENSE-DATA. See LICENSING.md.

Every card and page records the sources it draws on and the date each was read. Those sources keep their own licences.

Questions fréquentes

Qu'est-ce que ModelSpec ?

Find AI models that fit a job from your requirements, sourced benchmarks and real cost.

Comment installer ModelSpec ?

Il fonctionne comme serveur distant. Dans Claude Code : claude mcp add --transport http modelspec 'https://api.modelspec.dev/mcp' --header 'Authorization: <Required ModelSpec bearer API key. Get a key at https://modelspec.dev/pricing/.>'. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour ModelSpec ?

Oui. Il attend Authorization, à renseigner dans sa configuration.

ModelSpec est-il open source ?

Oui. Son code est sur GitHub sous licence MIT.

Qui maintient ModelSpec ?

Il est publié par turbobeest. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.