Add TokenLab model provider docs

docs.json

@@ -2037,6 +2037,18 @@
                               }
                             ]
                           },
+                          {
+                            "group": "TokenLab",
+                            "pages": [
+                              "models/providers/gateways/tokenlab/overview",
+                              {
+                                "group": "Usage",
+                                "pages": [
+                                  "models/providers/gateways/tokenlab/usage/basic"
+                                ]
+                              }
+                            ]
+                          },
                           {
                             "group": "Sambanova",
                             "pages": [
@@ -3947,6 +3959,18 @@
                           }
                         ]
                       },
+                      {
+                        "group": "TokenLab",
+                        "pages": [
+                          "models/providers/gateways/tokenlab/overview",
+                          {
+                            "group": "Usage",
+                            "pages": [
+                              "models/providers/gateways/tokenlab/usage/basic"
+                            ]
+                          }
+                        ]
+                      },
                       {
                         "group": "Sambanova",
                         "pages": [

models/providers/gateways/tokenlab/overview.mdx

@@ -0,0 +1,67 @@
+---
+title: TokenLab
+sidebarTitle: Overview
+description: Use TokenLab models with Agno agents.
+---
+
+TokenLab provides an OpenAI-compatible API for routing Agno agents across GPT, Claude, Gemini, DeepSeek, Qwen, Kimi, MiniMax, GLM, Grok, and other leading models through one endpoint.
+
+Explore available models from the [TokenLab model API](https://api.tokenlab.sh/v1/models).
+
+## Authentication
+
+Set your `TOKENLAB_API_KEY` environment variable. Get your API key from the [TokenLab dashboard](https://tokenlab.sh/dashboard).
+
+<CodeGroup>
+
+```bash Mac
+export TOKENLAB_API_KEY=***
+```
+
+```bash Windows
+setx TOKENLAB_API_KEY ***
+```
+
+</CodeGroup>
+
+## Example
+
+Use `TokenLab` with your `Agent`:
+
+<CodeGroup>
+
+```python agent.py
+from agno.agent import Agent
+from agno.models.tokenlab import TokenLab
+
+agent = Agent(model=TokenLab(id="gpt-5.4-mini"), markdown=True)
+
+# Print the response in the terminal
+agent.print_response("Share a 2 sentence horror story")
+```
+
+</CodeGroup>
+
+You can also use the model string shortcut:
+
+```python
+from agno.agent import Agent
+
+agent = Agent(model="tokenlab:gpt-5.4-mini", markdown=True)
+agent.print_response("Share a 2 sentence horror story")
+```
+
+<Note> View more examples [here](/models/providers/gateways/tokenlab/usage/basic). </Note>
+
+## Params
+
+| Parameter    | Type            | Default                         | Description                                                        |
+| ------------ | --------------- | ------------------------------- | ------------------------------------------------------------------ |
+| `id`         | `str`           | `"gpt-5.4-mini"`                | The id of the model to use through TokenLab                        |
+| `name`       | `str`           | `"TokenLab"`                    | The name of the model                                              |
+| `provider`   | `str`           | `"TokenLab"`                    | The provider of the model                                          |
+| `api_key`    | `Optional[str]` | `None`                          | The API key for TokenLab (defaults to TOKENLAB_API_KEY env var)    |
+| `base_url`   | `str`           | `"https://api.tokenlab.sh/v1"`  | The base URL for the TokenLab OpenAI-compatible API                |
+| `max_tokens` | `int`           | `1024`                          | The maximum number of tokens to generate                           |
+
+`TokenLab` also supports the params of [OpenAI](/reference/models/openai).

models/providers/gateways/tokenlab/usage/basic.mdx

@@ -0,0 +1,46 @@
+---
+title: Basic Agent
+---
+
+## Code
+
+```python cookbook/90_models/tokenlab/basic.py
+from agno.agent import Agent, RunOutput  # noqa
+from agno.models.tokenlab import TokenLab
+
+agent = Agent(
+    model=TokenLab(id="gpt-5.4-mini"),
+    markdown=True,
+)
+
+# Get the response in a variable
+# run: RunOutput = agent.run("Share a 2 sentence horror story")
+# print(run.content)
+
+# Print the response in the terminal
+agent.print_response("Share a 2 sentence horror story")
+```
+
+## Usage
+
+<Steps>
+  <Snippet file="create-venv-step.mdx" />
+
+  <Step title="Set your API key">
+    ```bash
+    export TOKENLAB_API_KEY=xxx
+    ```
+  </Step>
+
+  <Step title="Install dependencies">
+    ```bash
+    uv pip install -U agno openai
+    ```
+  </Step>
+
+  <Step title="Run Agent">
+    ```bash
+    python cookbook/90_models/tokenlab/basic.py
+    ```
+  </Step>
+</Steps>

models/providers/model-index.mdx

@@ -393,6 +393,14 @@ Browse the provider guides available in this documentation. Capabilities vary by
   >
     Route model requests through Requesty.
   </Card>
+  <Card
+    title="TokenLab"
+    icon="route"
+    iconType="duotone"
+    href="/models/providers/gateways/tokenlab/overview"
+  >
+    TokenLab multi-model gateway.
+  </Card>
   <Card
     title="SambaNova"
     icon="server"