Providers
gemini
Google Gemini chat adapter — Gemini 2.5 Pro / Flash. Streaming, tool-calls, vision, 1M+ context.
import { gemini } from '@agentskit/adapters'
const adapter = gemini({
apiKey: process.env.GOOGLE_API_KEY!,
model: 'gemini-2.5-flash',
})#Options
| Option | Type | Default |
|---|---|---|
apiKey | string | required |
model | string | required |
baseUrl | string | https://generativelanguage.googleapis.com |
apiVersion | string | v1beta |
fetch | typeof fetch | global |
#Model examples
gemini-2.5-pro · gemini-2.5-flash · gemini-2.5-flash-8b · gemini-2.0-flash-exp.
#Env
| Var | Purpose |
|---|---|
GOOGLE_API_KEY | API key from aistudio.google.com |
#Notes
- Streaming via SSE
streamGenerateContent. - Multimodal: inline image data or URI parts.
- For Vertex AI (IAM + GCP billing) use the forthcoming vertexAdapter.
#Related
Explore nearby
- PeerProviders
25 native chat and embedder adapters, plus higher-order adapters that compose candidates. Separate from the 140-provider models catalog.
- PeerChoosing an adapter
Capability decision table and rules of thumb for picking a chat adapter.
- PeerHosted chat adapters
17 managed-LLM adapters. Same contract; swap by changing one import.