diff --git a/docs/providers/gemini.md b/docs/providers/gemini.md index c2f20bda..911502d6 100644 --- a/docs/providers/gemini.md +++ b/docs/providers/gemini.md @@ -32,9 +32,9 @@ Zoo Code supports Google's Gemini family of models through the Google AI Gemini ## Available Models -Zoo Code supports all Gemini models available through Google's API and automatically tracks Google's latest stable releases. +Zoo Code's model catalog includes Gemini 3.7 Flash (`gemini-3.7-flash`), Google's generally available workhorse model for agentic coding and complex tasks. It supports text, image, video, audio, and PDF input, with a 1,048,576-token context window, up to 65,536 output tokens, and configurable `minimal`, `low`, `medium`, or `high` reasoning effort without a reasoning budget. -For the complete, up-to-date model list and capabilities, see [Google's Gemini models documentation](https://ai.google.dev/models/gemini). +For Google's complete, up-to-date model list and capabilities, see [the Gemini models documentation](https://ai.google.dev/gemini-api/docs/models). --- @@ -108,6 +108,7 @@ Search for the latest Node.js security vulnerabilities and then analyze my packa ## Tips and Notes * **Pricing:** Gemini API usage is priced based on input and output tokens. URL context and search grounding may incur additional costs. Some experimental models are available for free. Refer to the [Gemini pricing page](https://ai.google.dev/pricing) for detailed information. +* **Gemini 3.7 Flash introductory pricing:** Google lists Gemini 3.7 Flash at $0.75 per million input tokens and $3.75 per million output tokens through December 31, 2026. Standard pricing begins January 1, 2027. * **Model Selection:** Choose models based on your needs: - **Flash models:** Faster and more cost-effective for most tasks - **Pro models:** Better for complex reasoning and analysis diff --git a/docs/providers/vertex.md b/docs/providers/vertex.md index 944dbb54..8f011a63 100644 --- a/docs/providers/vertex.md +++ b/docs/providers/vertex.md @@ -37,6 +37,8 @@ Zoo Code supports accessing models through Google Cloud Platform's Vertex AI, a Zoo Code supports all models available through Google Cloud Vertex AI, including Anthropic Claude, Google Gemini, and MAAS (Model as a Service) offerings. +Gemini 3.7 Flash is available as `gemini-3.7-flash`. It is generally available on the global endpoint with a 1,048,576-token context window, up to 65,536 output tokens, multimodal input, and configurable reasoning effort. + For the complete, up-to-date model list and IDs, see [Vertex AI's models documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models). --- @@ -61,7 +63,7 @@ For the complete, up-to-date model list and IDs, see [Vertex AI's models documen * Or provide the file path in **Google Cloud Key File Path** field 4. **Enter Project ID:** Enter your Google Cloud Project ID. -5. **Select Region:** Choose the region where your Vertex AI resources are located (e.g., `us-east5`). +5. **Select Region:** Choose the region where your Vertex AI resources are located (e.g., `us-east5`). For Gemini 3.7 Flash, select `global`. 6. **Select Model:** Choose your desired model from the "Model" dropdown. --- @@ -110,3 +112,4 @@ URL Context and Google Search Grounding options only appear when a Gemini model * **Permissions:** Ensure your Google Cloud account has the necessary permissions to access Vertex AI and the specific models you want to use. * **Pricing:** Refer to the [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) page for details. +* **Gemini 3.7 Flash introductory pricing:** Google lists Gemini 3.7 Flash at $0.75 per million input tokens and $3.75 per million output tokens through December 31, 2026. Standard pricing begins January 1, 2027.