Model · Inception Labs

Mercury 2.5

inception/mercury-2.5

Inception's diffusion-based reasoning model — generates in parallel rather than token by token, for real-time chat, agents and structured output

reasoningcaching

Specs

Context

260K

Max output

16K

Provider

Inception Labs

Input

$0.040/ 1M tokens

Output

$0.150/ 1M tokens

Cache read

$0.0040/ 1M tokens

Try it

Chat with Mercury 2.5Terramind 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("mercury-2.5"),
  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