Property | Description | |||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Model ID | gemini-1.5-flash-001 | |||||||||||||||||
Alias | - | |||||||||||||||||
Creator | Google | |||||||||||||||||
License | - | |||||||||||||||||
Supported data types | InputsAudio, Image, Text, Video OutputsText | |||||||||||||||||
Token limits | Input token limit1,000,000 Output token limit8,192 | |||||||||||||||||
Capabilities | Adjustable safety settings Caching Code execution Function calling JSON mode JSON schema Structured outputs System instructions Tuning | |||||||||||||||||
Release date | ||||||||||||||||||
Latest update | ||||||||||||||||||
Knowledge cut-off | ||||||||||||||||||
Reference URL | https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models | |||||||||||||||||
Hugging Face URL | - | |||||||||||||||||
Providers
| ||||||||||||||||||
GatewayGlama gateway allows you to interact with leading AI models using OpenAI compatible API. import { OpenAI } from 'openai'
const openai = new OpenAI({
// OpenAI compatible API
baseURL: 'https://glama.ai/api/gateway/openai/v1',
// Your Glama Gateway API key
// https://glama.ai/settings
apiKey: GLAMA_API_KEY,
});
await openai.chat.completions.create({
messages: [
{
role: 'user',
content: 'Hello!'
}
],
// Let Glama choose the best provider
model: 'gemini-1.5-flash-001',
// or specify a specific provider...
// model: 'google-vertex/gemini-1.5-flash-001'
}); |