> ## Documentation Index
> Fetch the complete documentation index at: https://docs.freemodel.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Gemini generateContent

> Use the Gemini generateContent-compatible endpoint.

<Warning>
  This is a compatibility endpoint for existing Gemini-style integrations. For new integrations, use the [OpenAI-compatible API](/api-reference/chat-completions).
</Warning>

`POST https://api.freemodel.app/v1beta/models/{model}:generateContent`

Choose a Gemini-compatible model ID returned by [`GET /v1/models`](/api-reference/list-models). Substitute it for `<gemini-model-id>` in the path.

## Generate content

Authenticate with a Bearer key. The gateway also accepts a FreeModel key in the `key` query parameter for Gemini-style clients.

```bash theme={null}
curl "https://api.freemodel.app/v1beta/models/<gemini-model-id>:generateContent" \
  -H "Authorization: Bearer sk-xxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {"text": "Explain an API gateway in one sentence."}
        ]
      }
    ],
    "generationConfig": {
      "temperature": 0.2,
      "maxOutputTokens": 100
    }
  }'
```

```json Response theme={null}
{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "An API gateway provides a single entry point that routes requests to backend APIs."
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 9,
    "candidatesTokenCount": 15,
    "totalTokenCount": 24
  }
}
```

## Request body

| Field                              | Type    | Required | Description                                         |
| ---------------------------------- | ------- | -------- | --------------------------------------------------- |
| Path `model`                       | string  | Yes      | A Gemini-compatible model ID available to your key. |
| `contents`                         | array   | Yes      | Gemini-style content objects containing `parts`.    |
| `generationConfig.temperature`     | number  | No       | Sampling variation.                                 |
| `generationConfig.maxOutputTokens` | integer | No       | Maximum tokens to generate when supported.          |

<Note>
  Model availability can change. The [models page](https://freemodel.app/models) lists the current catalog and pricing.
</Note>