diff --git a/docs/core-concepts/models.mdx b/docs/core-concepts/models.mdx
index 89adb0a82..94a8bbb65 100644
--- a/docs/core-concepts/models.mdx
+++ b/docs/core-concepts/models.mdx
@@ -80,10 +80,10 @@ Pass `--model` and optionally `--provider` to `fabro run`:
 
 ```bash
 fabro run files-internal/demo/01-hello.dot --model claude-opus-4-6
-fabro run files-internal/demo/04-pipeline.dot --model gemini-3.1-pro-preview --provider gemini
+fabro run files-internal/demo/04-pipeline.dot --model gemini-3.1-pro-preview
 ```
 
-These flags set the default model for all nodes that don't have an explicit model assigned via a stylesheet.
+These flags set the default model for all nodes that don't have an explicit model assigned via a stylesheet. The provider is automatically inferred from the model catalog — you only need `--provider` for models not in the catalog or to force a specific provider.
 
 ### Run config TOML
 
@@ -96,7 +96,6 @@ graph = "implement.dot"
 
 [llm]
 model = "claude-sonnet-4-5"
-provider = "anthropic"
 
 [llm.fallbacks]
 anthropic = ["gemini", "openai"]
diff --git a/docs/execution/run-configuration.mdx b/docs/execution/run-configuration.mdx
index 92eff0619..a4b72172d 100644
--- a/docs/execution/run-configuration.mdx
+++ b/docs/execution/run-configuration.mdx
@@ -37,7 +37,6 @@ directory = "/tmp/workdir"
 
 [llm]
 model = "claude-sonnet-4-5"
-provider = "anthropic"
 
 [llm.fallbacks]
 anthropic = ["gemini", "openai"]
@@ -108,13 +107,12 @@ Override the default model and provider for all nodes that don't have an explici
 ```toml title="run.toml"
 [llm]
 model = "claude-sonnet-4-5"
-provider = "anthropic"
 ```
 
 | Field | Description |
 |---|---|
 | `model` | Model ID or alias (e.g. `claude-sonnet-4-5`, `opus`, `gemini-pro`). See [Models](/core-concepts/models). |
-| `provider` | Provider name: `anthropic`, `openai`, `gemini`, `kimi`, `zai`, `minimax`, `inception`. |
+| `provider` | Provider name (optional — auto-inferred from the model catalog). Only needed for models not in the catalog or to force a specific provider. |
 
 #### `[llm.fallbacks]`
 
diff --git a/docs/reference/dot-language.mdx b/docs/reference/dot-language.mdx
index 97a954737..a38063c3a 100644
--- a/docs/reference/dot-language.mdx
+++ b/docs/reference/dot-language.mdx
@@ -200,7 +200,7 @@ Start nodes can also be identified by ID (`start` or `Start`). Exit nodes can be
 | `fidelity` | String | How much prior context is passed: `compact`, `full`, `summary:high`, `summary:medium`, `summary:low`, `truncate` |
 | `thread_id` | String | Groups nodes into a shared conversation thread |
 | `model` | String | Explicit model ID (overrides stylesheet) |
-| `provider` | String | Explicit provider name (overrides stylesheet) |
+| `provider` | String | Explicit provider name (overrides stylesheet). Auto-inferred from the model catalog when omitted. |
 | `project_memory` | Boolean | When `true` (default), prompt nodes discover and include project docs (`AGENTS.md`, `CLAUDE.md`, etc.) as a system prompt. Set to `false` to disable. |
 | `backend` | String | Agent execution backend. `api` (default): Fabro calls the LLM API directly and runs its own tool loop. `cli`: Fabro delegates to an external CLI tool (`claude`, `codex`, or `gemini` based on provider). See [Agents — Backends](/core-concepts/agents#backends). |
 
diff --git a/docs/tutorials/multi-model.mdx b/docs/tutorials/multi-model.mdx
index 8d11c7727..790a9e7ac 100644
--- a/docs/tutorials/multi-model.mdx
+++ b/docs/tutorials/multi-model.mdx
@@ -86,7 +86,7 @@ Stylesheets support four properties:
 | Property | Description |
 |---|---|
 | `model` | Model ID or alias (e.g. `claude-sonnet-4-5`, `opus`, `gemini-pro`) |
-| `provider` | Provider name (`anthropic`, `openai`, `gemini`, etc.) |
+| `provider` | Provider name (optional — auto-inferred from the model catalog when omitted) |
 | `reasoning_effort` | `low`, `medium`, or `high` |
 | `backend` | `api` (default) or `cli` |
 
diff --git a/docs/workflows/stylesheets.mdx b/docs/workflows/stylesheets.mdx
index f6db0489d..d1ca4c552 100644
--- a/docs/workflows/stylesheets.mdx
+++ b/docs/workflows/stylesheets.mdx
@@ -65,7 +65,7 @@ Stylesheets support four properties:
 | Property | Description | Example |
 |---|---|---|
 | `model` | Model ID or alias | `claude-sonnet-4-5`, `opus`, `gemini-pro` |
-| `provider` | Provider name | `anthropic`, `openai`, `gemini` |
+| `provider` | Provider name (optional — auto-inferred from the model catalog when omitted) | `anthropic`, `openai`, `gemini` |
 | `reasoning_effort` | Reasoning effort level | `low`, `medium`, `high` |
 | `backend` | Agent execution backend — `api` (default) runs Fabro's own tool loop, `cli` delegates to an external CLI tool. See [Backends](/core-concepts/agents#backends). | `cli`, `api` |
 
diff --git a/skills/fabro-create-workflow/references/dot-language.md b/skills/fabro-create-workflow/references/dot-language.md
index e4dc84c54..d4f6cbaa3 100644
--- a/skills/fabro-create-workflow/references/dot-language.md
+++ b/skills/fabro-create-workflow/references/dot-language.md
@@ -164,7 +164,7 @@ graph [model_stylesheet="
 
 Selectors by specificity (low to high): `*` (universal, 0), shape name (1), `.class` (2), `#nodeid` (3). Higher specificity wins. Same specificity: last rule wins. Explicit node attributes override stylesheets.
 
-Properties: `model`, `provider`, `reasoning_effort`, `backend`.
+Properties: `model`, `provider` (optional — auto-inferred from the model catalog), `reasoning_effort`, `backend`.
 
 **Critical:** Use semicolons between properties (e.g. `model: foo; provider: bar;`).