- functions
- 2
- access
- Your key
- tasks
- 2
Use Gemini API on Longwave
- Download Longwave or open app.longwave.run.
- Add your Gemini API API key once in Longwave settings. Calls run on your Gemini API account at Gemini API's price.
- Ask for the result in any thread, for example: “Draft text for a research brief”. The agent picks the Gemini API function and calls it.
Use Gemini API in Claude Code, Codex, Cursor or ChatGPT
Add the Longwave MCP server once. It carries 2,593 functions across 103 tools, including Gemini API, and asks you to sign in on first use.
Why call Gemini API through Longwave
- Your Gemini API key is stored once, encrypted, and used by every harness and device you use.
- One MCP server for 103 tools, so your agent setup does not grow a key and a server per vendor.
- Spending limits per key and per account, checked before a paid call is made.
- Each call is recorded with the provider, the cost and the result, and can be read again from another device.
Gemini API functions
Gemini 1
| Function | Price |
|---|---|
| Get a response from Gemini Accepts a model name, text content and an output token limit and returns a model response to the supplied text content. google-ai.content.generate | The selected model and usage determine the charge; no single per-call price applies to this function. |
Google-Ai 1
| Function | Price |
|---|---|
| List Gemini models Accepts a page size and an optional pagination token and returns Gemini model names and metadata. google-ai.models.list | Model or provider metadata lookup; no generation charge or separate published per-call fee. |
Prices are Gemini API's published rates. Source: Gemini API pricing.
Use cases
- Draft text for a research brief Submit the supplied text to the selected Gemini model.
- List Gemini models before writing an integration Retrieve the available model names and metadata.
- Generate a text response for a content draft Request a response using the model and output limit in the function inputs.