api-access: the typical model entry uses the stable aliases

The gateway now serves four version-free names (deepseek-flash-latest,
glm-flash-latest, deepseek-flash-tee, glm-tee), added per co-op/support#47 so a
member's config survives a provider retiring a version. The example entry is what
members copy, so it should be the names that keep working; provider-prefixed ids
still work and are linked for anyone who needs a specific version.
This commit is contained in:
inference-admin committed 2026-11-14 18:42:47 +00:00
1 parent 808e54505f
commit 7f8480f13d
1 file changed
+14 -5
+14 -5
View File
@@ -98,7 +98,8 @@ endpoint configuration:
- **API type / protocol:** "OpenAI compatible" (or `openai-completions` where a
protocol string must be named) — not "Ollama", "Anthropic", or "Responses"
- **API key:** your member key (the `sk-…` string)
- **Model:** one from the [model list](models.md), e.g. `tinfoil/deepseek-v4-1-flash` or `greenpt/glm-5.3-flash`
- **Model:** a **stable alias** — `deepseek-flash-latest`, `glm-flash-latest`, `deepseek-flash-tee`, or
`glm-tee` — or any id from the [model list](models.md), e.g. `tinfoil/deepseek-v4-1-flash`
A typical provider entry looks like:
@@ -110,16 +111,24 @@ A typical provider entry looks like:
"api": "openai-completions",
"apiKey": "sk-your-key",
"models": [
{ "id": "tinfoil/deepseek-v4-1-flash" },
{ "id": "tinfoil/gpt-oss-120b" },
{ "id": "tinfoil/glm-5.3" },
{ "id": "greenpt/glm-5.3-flash" }
{ "id": "deepseek-flash-latest" },
{ "id": "glm-flash-latest" },
{ "id": "deepseek-flash-tee" },
{ "id": "glm-tee" }
]
}
}
}
```
The four names in `models` are **stable aliases**: we re-point them when a
provider retires or replaces a model, so a config that pins one keeps working
across transitions. `-latest` is the default route for a family (renewable energy,
policy-based privacy); `-tee` serves the same family inside attested hardware.
Pricing is set at the alias, so a transition that changes price appears in the
model list rather than arriving as a surprise. If you need one particular version,
use the provider-prefixed id from the [model list](models.md) instead.
If a tool's own docs show a local-server example (e.g.
`baseUrl: http://localhost:11434/v1` with `api: "openai-completions"`),
substitute our base URL and your member key for `apiKey` — the protocol value