> For the complete documentation index, see [llms.txt](https://docs.otari.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.otari.ai/self-hosting/providers/gemini.md). # Connect Gemini Serve Google's Gemini models through Otari with a Gemini API key from Google AI Studio. For Gemini on Google Cloud, use the `vertexai` provider instead. See any-llm's [supported providers](https://docs.mozilla.ai/any-llm/providers/) for the current provider list and [Models](https://docs.otari.ai/reference/gateway/models) for Otari's model-name format. ## Before you start * A running Otari with `OTARI_SECRET_KEY` set, and its master key. The [Self-hosted quickstart](/self-hosting/self-hosted-quickstart.md) sets up both. * A Gemini API key from . ## Add the key Add Gemini as a hosted provider, on **Hosted providers** in the dashboard's deployment view or through the API: ```bash curl -X POST http://localhost:8000/api/v1/hosted-providers \ -H "Authorization: Bearer $OTARI_MASTER_KEY" \ -H "Content-Type: application/json" \ -d '{"provider": "gemini", "api_key": "AIza..."}' ``` Otari stores the key encrypted and offers every model Gemini lists on it; each model with a price is switched on, and an unpriced model arrives switched off. To keep the provider in configuration instead, declare it under `hosted_providers:` in `config.yml` (see [Hosted providers in config.yml](/self-hosting/configuration.md#hosted-providers-in-configyml)). Otari does not read `GEMINI_API_KEY` from its environment unless a declaration names it; see [Configuring a provider](https://docs.otari.ai/reference/gateway/models#configuring-a-provider). ## Choose a model Models are addressed as `gemini:`: ``` gemini:gemini-3-flash-preview gemini:gemini-3.1-flash-lite ``` Everything after the colon is passed to Gemini. A model is served once it is switched on under the provider on the Hosted providers page. Google retires older models for new keys, so check the [model list](https://ai.google.dev/gemini-api/docs/models) if a name is rejected. Chat completions take only text-generation models. Send an embedding model such as `gemini-embedding-001` to `POST /api/v1/embeddings` instead (see the [API reference](https://docs.otari.ai/reference)). ## Verify Make a request with your Otari API key (`tk-...`) through the OpenAI client (`pip install openai`): ```python from openai import OpenAI client = OpenAI(base_url="http://localhost:8000/api/v1", api_key="tk-...") resp = client.chat.completions.create( model="gemini:gemini-3-flash-preview", messages=[{"role": "user", "content": "Say hello in five words."}], ) print(resp.choices[0].message.content) ``` Expected (sample) output: ``` Hello there, how are you? ``` ## Troubleshooting | Symptom | Likely cause | | ------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | HTTP 424 (code `provider_not_configured`) | Nothing serves the model: no Gemini provider is configured, it is switched off, or the model is not switched on under it. Switch the model on under Gemini on the Hosted providers page. | | HTTP 400 `API key not valid. Please pass a valid API key.` | Gemini rejected the key Otari sent. Replace it where the provider is configured: on the Hosted providers page, or in its `hosted_providers:` entry (or the variable that entry names, such as `GEMINI_API_KEY`) in `config.yml`. | | HTTP 404 `This model ... is no longer available to new users` | Google has retired that model for new keys. Use the model the message suggests. | | HTTP 429 `You exceeded your current quota` (code `upstream_rate_limited`) | Your key's quota for that model is used up or is zero, which is common for Pro models on the free tier. Wait, pick another model, or enable billing in Google AI Studio. | | HTTP 502 `The provider failed the request with HTTP 503` | Gemini is overloaded or failed on its side. These are retryable. | | HTTP 402 `No pricing configured for model ...` | The model has no price and `require_pricing` rejected the request. Set a price for it on the Hosted providers page or in a `pricing:` entry, or enable `default_pricing: true`. | --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.otari.ai/self-hosting/providers/gemini.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.