OpenRouter: where a model slug lives

Where the model id lives

The quickstart sends POST /api/v1/chat/completions with a model field. Its example is ~openai/gpt-sol-latest. The page says that value is a latest alias that always resolves to the newest model in the OpenAI GPT Sol family, and that you can substitute any model slug.

The same page shows the slug on the OpenAI SDK pointed at https://openrouter.ai/api/v1, on the OpenRouter Python and TypeScript SDKs, and on the Agent SDK callModel model field. This page does not include an API key.

model = "~openai/gpt-sol-latest"

Source: OpenRouter quickstart , checked October 25, 2026.

How to pin or swap it

To pin, replace the ~ alias with a specific slug from the OpenRouter catalog. To swap a provider id that is shutting down, use the official replacement from the table as that slug. OpenRouter slugs are prefixed with the provider, so an OpenAI id gpt-4o is not always the same string as the OpenRouter slug.

The model fallbacks guide says the models array is tried in order when the first model returns an error. The swap guide quotes that page, including the extra_body.models shape used with the OpenAI SDK. The ids in that sample are the guide's examples.

model = "~openai/gpt-sol-latest"
extra_body = {
    "models": ["~anthropic/claude-sonnet-latest", "gryphe/mythomax-l2-13b"]
}

Sources: OpenRouter quickstart , OpenRouter model fallbacks , checked October 25, 2026.

GPT-6 function tools

The quickstart posts to /api/v1/chat/completions. It does not document a Responses API switch, so this page does not invent one.

If the slug you send is an OpenAI model, OpenAI's Using GPT-6 guide still applies to that provider: GPT-6 Astra and GPT-6.1 Sol tool calling requires the Responses API, and GPT-6 Sol and GPT-6 Luna accept function tools on Chat Completions only with reasoning effort none. Read the error pages before you send tools.

Sources: OpenRouter quickstart , Using GPT-6 , checked October 25, 2026.

Upcoming shutdowns in this dataset

gpt-4.1-2025-04-14, gpt-4.1-mini-2025-04-14, gpt-4o-2024-08-06, gpt-4o-2024-11-20, and gpt-4o-mini-2024-07-18 shut down on 2027-01-14. The official replacement on these rows is gpt-6-luna.

gpt-4.1, gpt-4.1-mini, gpt-4o, and gpt-4o-mini have no shutdown date on their own records. A request that sends the short id is not the dated snapshot row. Open the model page before you treat the short id as shut down.

Rows are upcoming OpenAI chat models in the gpt-4o, gpt-4.1, gpt-4-turbo, gpt-4, and gpt-3.5-turbo families. Audio, realtime, transcribe, and search ids are not in this table. The same id on another platform is in the other-platforms column. The full calendar is upcoming shutdowns. Provider wording for the shutdown day is on what happens on shutdown day.

Detect a dying model

These checks read SunsetDiff. They do not call the model provider.

• upcoming.json lists dated shutdowns in the next 90 days. No API key. Field notes are on the API docs.
• lookup/gpt-4o.json reads one id. Replace gpt-4o with the string in your config.
• The MCP server tools are check_model, upcoming_shutdowns, migration_diff, and scan_text.
• A status badge shows the stored status for a model page.
• The scan page builds a local search for retiring ids. Nothing is uploaded.

Questions