Gemini API Gateway, Pricing & Request Examples
Learn how to connect Gemini through ai2save, check current public model prices and context tiers, and send a native generateContent request.
Gemini API for text and supported multimodal tasks
Gemini models can be used for text generation and, where supported by the selected model and route, multimodal input. Check the current group catalog for exact model IDs and pricing rather than treating all Gemini variants as interchangeable.
Public prices
USD / 1M tokens
No public prices are currently available for this series. Check model access and billing rules for your selected group in the console.
Standard-time prices. Context tiers, cache duration, time multipliers and per-request units are listed below. The selected group’s billing rules apply.
Source: OpenAI · Anthropic · Gemini · LiteLLM — Not independently verified
Integration and request example
Use the native Gemini generateContent endpoint at /v1beta/models/{model}:generateContent with x-goog-api-key authentication. Select a key bound to a Gemini-compatible group. The general API scripting guide also explains client configuration and error handling.
Replace YOUR_MODEL_ID with a model ID supported by your group set SUB2API_API_KEY, and set SUB2API_BASE_URL to the service origin (without /v1). This example shows the request format and does not send a request.
curl "$SUB2API_BASE_URL/v1beta/models/YOUR_MODEL_ID:generateContent" \
-H "x-goog-api-key: $SUB2API_API_KEY" \
-H "Content-Type: application/json" \
-d '{"contents":[{"parts":[{"text":"Hello"}]}]}'Read the integration guide →Model limits and billing conditions
Context tiers, output limits and supported input types vary by model. Text-token prices do not establish image, audio or video charges. Verify the billing mode and permissions of the chosen group before sending multimodal or long-context requests.
View all API prices →