Back to models
Try in Agents
Model · Google
Gemma 4
google/gemma-4
Google's open-weight MoE model (26B total, 4B active) with vision and tool calling
visionvideocaching
Specs
Context
262K
Max output
16K
Provider
Google
Input
$0.150/ 1M tokens
Output
$0.600/ 1M tokens
Cache read
$0.015/ 1M tokens
Try it
Chat with Gemma 4Terramind API
⌘+Enter to run
Code
import { streamText } from "ai";
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
const terramind = createOpenAICompatible({
name: "terramind",
baseURL: "https://terramind.com/api/v1",
apiKey: process.env.TERRAMIND_API_KEY!,
});
const result = streamText({
model: terramind("gemma-4"),
prompt: "Why is the sky blue?",
});
for await (const chunk of result.textStream) {
process.stdout.write(chunk);
}
Want to run this in your app? Grab an API key · Full chat reference
More by Google
| Model | Context | In | Out | Capabilities |
|---|---|---|---|---|
| 1.0M | $1.25 | $10.00 | reasoningvisionvideo | |
| 1.0M | $2.00 | $12.00 | reasoningvisionvideo | |
| 1M | $1.50 | $9.00 | reasoningvisionvideo | |
| 1M | $0.750 | $3.75 | reasoningvisionvideo | |
| 1M | $0.750 | $3.75 | reasoningvisionvideo | |
| 1M | $0.750 | $3.75 | reasoningvisionvideo | |
| 1M | $4.00 | $20.00 | reasoningvisionvideo | |
| 1M | $0.250 | $1.50 | visionvideoaudio |