---
title: "/generateContent"
url: "/en/docs/generateContent"
canonical_url: "https://docs.litellm.ai/en/docs/generateContent"
type: "docs"
summary: "Use LiteLLM to call Google AI's generateContent endpoints for text generation, multimodal interactions, and streaming responses."
related:
  - "/en/docs/evals_api"
  - "/en/docs/apply_guardrail"
---
# /generateContent

> Index of all LiteLLM docs: https://docs.litellm.ai/llms.txt


Use LiteLLM to call Google AI's generateContent endpoints for text generation, multimodal interactions, and streaming responses.

## Overview 

| Feature | Supported | Notes | 
|-------|-------|-------|
| Cost Tracking | ✅ |  |
| Logging | ✅ | works across all integrations |
| End-user Tracking | ✅ | |
| Streaming | ✅ | |
| Fallbacks | ✅ | between supported models |
| Loadbalancing | ✅ | between supported models |
| Metadata Tracking | ✅ | passes trace ID, metadata to observability callbacks (e.g. S3, Langfuse) |

## Usage 
---

### LiteLLM Python SDK 

**Basic Usage**

#### Non-streaming example
```python showLineNumbers title="Basic Text Generation"
from litellm.google_genai import agenerate_content
from google.genai.types import ContentDict, PartDict
import os

# Set API key
os.environ["GEMINI_API_KEY"] = "your-gemini-api-key"

contents = ContentDict(
    parts=[
        PartDict(text="Hello, can you tell me a short joke?")
    ],
    role="user",
)

response = await agenerate_content(
    contents=contents,
    model="gemini/gemini-3.8-flash",
    max_tokens=100,
)
print(response)
```

#### Streaming example
```python showLineNumbers title="Streaming Text Generation"
from litellm.google_genai import agenerate_content_stream
from google.genai.types import ContentDict, PartDict
import os

# Set API key
os.environ["GEMINI_API_KEY"] = "your-gemini-api-key"

contents = ContentDict(
    parts=[
        PartDict(text="Write a long story about space exploration")
    ],
    role="user",
)

response = await agenerate_content_stream(
    contents=contents,
    model="gemini/gemini-3.8-flash",
    max_tokens=500,
)

async for chunk in response:
    print(chunk)
```

**Sync Usage**

#### Sync non-streaming example
```python showLineNumbers title="Sync Text Generation"
from litellm.google_genai import generate_content
from google.genai.types import ContentDict, PartDict
import os

# Set API key
os.environ["GEMINI_API_KEY"] = "your-gemini-api-key"

contents = ContentDict(
    parts=[
        PartDict(text="Hello, can you tell me a short joke?")
    ],
    role="user",
)

response = generate_content(
    contents=contents,
    model="gemini/gemini-3.8-flash",
    max_tokens=100,
)
print(response)
```

#### Sync streaming example
```python showLineNumbers title="Sync Streaming Text Generation"
from litellm.google_genai import generate_content_stream
from google.genai.types import ContentDict, PartDict
import os

# Set API key
os.environ["GEMINI_API_KEY"] = "your-gemini-api-key"

contents = ContentDict(
    parts=[
        PartDict(text="Write a long story about space exploration")
    ],
    role="user",
)

response = generate_content_stream(
    contents=contents,
    model="gemini/gemini-3.8-flash",
    max_tokens=500,
)

for chunk in response:
    print(chunk)
```

### LiteLLM Proxy Server 

1. Setup config.yaml

```yaml
model_list:
    - model_name: gemini-flash
      litellm_params:
        model: gemini/gemini-3.8-flash
        api_key: os.environ/GEMINI_API_KEY
```

2. Start proxy 

```bash
litellm --config /path/to/config.yaml
```

3. Test it! 

**Google GenAI SDK**

```python showLineNumbers title="Google GenAI SDK with LiteLLM Proxy"
from google.genai import Client
import os

# Configure Google GenAI SDK to use LiteLLM proxy
os.environ["GOOGLE_GEMINI_BASE_URL"] = "http://localhost:4000"
os.environ["GEMINI_API_KEY"] = "sk-<your-litellm-api-key>"

client = Client()

response = client.models.generate_content(
    model="gemini-flash",
    contents=[
        {
            "parts": [{"text": "Write a short story about AI"}],
            "role": "user"
        }
    ],
    config={"max_output_tokens": 100}
)
```

**curl**

#### Generate Content

```bash showLineNumbers title="generateContent via LiteLLM Proxy"
curl -L -X POST 'http://localhost:4000/v1beta/models/gemini-flash:generateContent' \
-H 'content-type: application/json' \
-H "authorization: Bearer $LITELLM_API_KEY" \
-d '{
  "contents": [
    {
      "parts": [
        {
          "text": "Write a short story about AI"
        }
      ],
      "role": "user"
    }
  ],
  "generationConfig": {
    "maxOutputTokens": 100
  }
}'
```

#### Stream Generate Content

```bash showLineNumbers title="streamGenerateContent via LiteLLM Proxy"
curl -L -X POST 'http://localhost:4000/v1beta/models/gemini-flash:streamGenerateContent' \
-H 'content-type: application/json' \
-H "authorization: Bearer $LITELLM_API_KEY" \
-d '{
  "contents": [
    {
      "parts": [
        {
          "text": "Write a long story about space exploration"
        }
      ],
      "role": "user"
    }
  ],
  "generationConfig": {
    "maxOutputTokens": 500
  }
}'
```

## Native request fields

The `generateContent` endpoint is a drop-in for Google's [Generative Language REST API](https://ai.google.dev/api/generate-content), so the top-level fields that Google's `GenerateContentRequest` carries as siblings of `generationConfig` are forwarded to Google verbatim. This covers `safetySettings`, `toolConfig`, `cachedContent`, and `labels`. Send them at the top level of the request body exactly as you would when calling Google directly; there is no need to wrap them in `extra_body`. If you do pass `extra_body`, an explicit value there wins on conflict.

**curl**

```bash showLineNumbers title="Native top-level fields via LiteLLM Proxy"
curl -L -X POST 'http://localhost:4000/v1beta/models/gemini-flash:generateContent' \
-H 'content-type: application/json' \
-H "authorization: Bearer $LITELLM_API_KEY" \
-d '{
  "contents": [
    {
      "parts": [{"text": "Say hi"}],
      "role": "user"
    }
  ],
  "generationConfig": {
    "maxOutputTokens": 100
  },
  "safetySettings": [
    {
      "category": "HARM_CATEGORY_HATE_SPEECH",
      "threshold": "BLOCK_NONE"
    }
  ],
  "toolConfig": {
    "functionCallingConfig": {"mode": "AUTO"}
  }
}'
```

**LiteLLM Python SDK**

```python showLineNumbers title="Native top-level fields via LiteLLM Python SDK"
from litellm.google_genai import generate_content
import os

# Set API key
os.environ["GEMINI_API_KEY"] = "your-gemini-api-key"

response = generate_content(
    model="gemini/gemini-3.8-flash",
    contents=[{"role": "user", "parts": [{"text": "Say hi"}]}],
    safetySettings=[
        {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "BLOCK_NONE"}
    ],
    toolConfig={"functionCallingConfig": {"mode": "AUTO"}},
)
print(response)
```

## Related 

- [Use LiteLLM with gemini-cli](../docs/tutorials/litellm_gemini_cli)

## Related pages

- [/evals](https://docs.litellm.ai/en/docs/evals_api.md)
- [/guardrails/apply_guardrail](https://docs.litellm.ai/en/docs/apply_guardrail.md)