# Gemini (/docs/api/gemini)

The Gemini endpoints work with the Google Gen AI SDKs and take the model in the URL, as Google's API does. Gemini models and every other chat model in the catalog answer with a `GenerateContentResponse`.

| | |
|---|---|
| Generate | `POST https://api.ohmygpt.com/v1/models/{model}:generateContent` |
| Stream | `POST https://api.ohmygpt.com/v1/models/{model}:streamGenerateContent` |
| SDK base URL | `https://api.ohmygpt.com`, API version `v1` |
| Auth | `x-goog-api-key: $OHMYGPT_API_KEY` or `Authorization: Bearer $OHMYGPT_API_KEY` |

`{model}` is a full model ID from `GET /v1/models`, slash included: `/v1/models/google/gemini-3.1-flash-lite:generateContent`. Set the SDK's API version to `v1`, as below.

```python tab="Python"
import os
from google import genai
from google.genai import types

client = genai.Client(
    api_key=os.environ["OHMYGPT_API_KEY"],
    http_options=types.HttpOptions(base_url="https://api.ohmygpt.com", api_version="v1"),
)

response = client.models.generate_content(
    model="google/gemini-3.1-flash-lite",
    contents="Explain QUIC in two sentences.",
)
print(response.text)

for chunk in client.models.generate_content_stream(
    model="google/gemini-3.1-flash-lite",
    contents="Explain QUIC in two sentences.",
):
    print(chunk.text or "", end="")
```

```bash tab="cURL"
curl "https://api.ohmygpt.com/v1/models/ohmygpt/mock:generateContent" \
  -H "x-goog-api-key: $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents": [{"role": "user", "parts": [{"text": "ping"}]}]}'
```

```json
{
  "candidates": [
    {
      "index": 0,
      "finishReason": "STOP",
      "content": {
        "role": "model",
        "parts": [{ "text": "This is a mock reply from OhMyGPT. Your integration works; switch to a real model when ready." }]
      }
    }
  ],
  "usageMetadata": { "promptTokenCount": 15, "candidatesTokenCount": 17, "totalTokenCount": 32 }
}
```

## Safety settings [#safety-settings]

When a request has no `safetySettings`, OhMyGPT sets `HARM_CATEGORY_HARASSMENT`, `HARM_CATEGORY_HATE_SPEECH`, `HARM_CATEGORY_SEXUALLY_EXPLICIT`, and `HARM_CATEGORY_DANGEROUS_CONTENT` to `"threshold": "OFF"`. To filter, send your own `safetySettings`; Gemini models receive them unchanged.

```json
{
  "contents": [{ "role": "user", "parts": [{ "text": "ping" }] }],
  "safetySettings": [
    { "category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "BLOCK_MEDIUM_AND_ABOVE" }
  ]
}
```

## Other models [#other-models]

GPT, Claude, and every other chat model accept the same request. `systemInstruction`, `contents`, `tools`, `toolConfig`, and `thinkingConfig` ([Thinking](/docs/api/thinking)) carry over, and so does every `generationConfig` setting the model has an equivalent for. A setting it has no equivalent for, such as `seed` on Claude, isn't sent, and the model answers with its own default for it. Other models return one candidate per request, so `candidateCount` above 1 returns 400 naming `generationConfig.candidateCount`. `safetySettings` is not sent to other models. `cachedContent` is a Gemini feature; use it with Gemini models.

## Streaming [#streaming]

`:streamGenerateContent` answers with server-sent events, with or without `?alt=sse`. Each event is a `GenerateContentResponse` chunk. The chunk with `finishReason` ends the content, and the last chunk carries `usageMetadata`:

```text
data: {"candidates":[{"content":{"role":"model","parts":[{"text":" ready."}]},"index":0}]}

data: {"candidates":[{"content":{"role":"model","parts":[]},"finishReason":"STOP","index":0}]}

data: {"usageMetadata":{"promptTokenCount":29,"candidatesTokenCount":17,"totalTokenCount":46},"candidates":[{"content":{"role":"model","parts":[]},"index":0}]}
```

To see what a Gemini stream cost, look it up with the stream's `X-Request-ID` header; see [Cost of a stream](/docs/api/streaming#cost-of-a-stream).

## Errors [#errors]

Errors use Google's `google.rpc.Status` format:

```json
{
  "error": {
    "code": 404,
    "status": "NOT_FOUND",
    "message": "The model `google/gemini-0-nonexistent` does not exist. List available models with `GET /v1/models`.",
    "details": [
      { "@type": "type.googleapis.com/google.rpc.ErrorInfo", "reason": "MODEL_NOT_FOUND", "domain": "ohmygpt.com" }
    ]
  }
}
```