How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

choose-models - Prompt - OpenSmartRoute

Promptv1.0.0

choose-models

Name: choose-models
Author: albegali

Choose the model per tier for each vendor/tool, then regenerate the adapters

by albegali(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Prompt file imported from albegali/agentic-portal (.codex/prompts/choose-models.md). Fill in {{arguments}} before use. Copyright stays with the author.

Recommended model: gpt-5-mini (codex -p fast) (tier fast, see models.toml). Switch to it before running this command.

Arguments: {{arguments}}

Read models.toml. Show a compact table tier × enabled tool with the current model, and mark entries flagged "verify".
Ask the user, one question per tool, which model to use per tier (offer the current value as default; propose the vendor's latest small / mid / large model for fast / balanced / deep). If a web search tool is available, verify the current model names first.
Update models.toml (keep comments), run make agents. If the balanced model changed, also set "model" in .claude/settings.json to it (session default for follow-ups), unless the user wants to keep their own. Then make check. Chat: the final table, nothing else.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

<!-- Generated by tools/render_agents.py from workflow/workflow.toml and models.toml — do not edit; run `make agents`. -->
> Recommended model: **gpt-5-mini** (`codex -p fast`) (tier `fast`, see models.toml). Switch to it before running this command.

Arguments: {{arguments}}
1. Read `models.toml`. Show a compact table tier × enabled tool with the current model, and mark entries flagged "verify".
2. Ask the user, one question per tool, which model to use per tier (offer the current value as default; propose the vendor's latest small / mid / large model for fast / balanced / deep). If a web search tool is available, verify the current model names first.
3. Update `models.toml` (keep comments), run `make agents`. If the balanced model changed, also set `"model"` in `.claude/settings.json` to it (session default for follow-ups), unless the user wants to keep their own. Then `make check`.
Chat: the final table, nothing else.

Installed into a catalogue, chosen by a router

Install choose-models and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Photo: RDNE Stock project

For the business

What it costs to adopt - in engineering time.

Same client, same code
One base URL
The OpenAI-compatible endpoint answers your existing SDK calls; model=auto lets the router choose.
The SDKs
One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
Next eligible model answers
Failover built in
When a provider is down or over quota the request moves on; the trace says it did.

Manifest

The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.

albegali-agentic-portal-choose-models-codex-prompt.prompt.jsonjson

{
  "prompt": "<!-- Generated by tools/render_agents.py from workflow/workflow.toml and models.toml — do not edit; run `make agents`. -->\n> Recommended model: **gpt-5-mini** (`codex -p fast`) (tier `fast`, see models.toml). Switch to it before running this command.\n\nArguments: {{arguments}}\n1. Read `models.toml`. Show a compact table tier × enabled tool with the current model, and mark entries flagged \"verify\".\n2. Ask the user, one question per tool, which model to use per tier (offer the current value as default; propose the vendor's latest small / mid / large model for fast / balanced / deep). If a web search tool is available, verify the current model names first.\n3. Update `models.toml` (keep comments), run `make agents`. If the balanced model changed, also set `\"model\"` in `.claude/settings.json` to it (session default for follow-ups), unless the user wants to keep their own. Then `make check`.\nChat: the final table, nothing else.",
  "variables": [
    "arguments"
  ],
  "notes": "Choose the model per tier for each vendor/tool, then regenerate the adapters Arguments: [vendor or tool].",
  "metadata": {
    "source": {
      "provider": "github-codex-prompts",
      "repository": "https://github.com/albegali/agentic-portal",
      "path": ".codex/prompts/choose-models.md",
      "ref": "0694fcfa6f9f742ee5403ca5c19a53b6c55c6d0c",
      "url": "https://github.com/albegali/agentic-portal/blob/0694fcfa6f9f742ee5403ca5c19a53b6c55c6d0c/.codex/prompts/choose-models.md",
      "key": "albegali/agentic-portal/.codex/prompts/choose-models.md"
    }
  }
}

Fetch it by URL: GET /api/v1/registry/albegali-agentic-portal-choose-models-codex-prompt/manifest?version=1.0.0

About

Use it

Install choose-models and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Manifest

Reviews