Back to models
Try in Agents
Model · Xiaomi
MiMo V2.6 Pro UltraSpeed
xiaomi/mimo-v2.6-pro-ultraspeed
MiMo V2.6 Pro on accelerated inference, for interactive agents where latency matters — same model, 10x the price
reasoningvisionvideoaudiocachingfast
Specs
Context
1.0M
Max output
33K
Provider
Xiaomi
Input
$4.35/ 1M tokens
Output
$8.70/ 1M tokens
Cache read
$0.036/ 1M tokens
Try it
Chat with MiMo V2.6 Pro UltraSpeedTerramind 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("mimo-v2.6-pro-ultraspeed"),
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 Xiaomi
| Model | Context | In | Out | Capabilities |
|---|---|---|---|---|
| 1.0M | $0.435 | $0.870 | reasoningvisionvideo | |
| 1.0M | $0.140 | $0.280 | reasoningvisionvideo |