Model · Thinking Machines

Inkling

thinkingmachines/inkling

Try in Agents

Thinking Machines' first model — a 975B/41B multimodal MoE with text, image, and audio inputs (served via Baseten)

visionaudiocaching

Specs

Context

256K

Max output

256K

Provider

Thinking Machines

Input

$1.00/ 1M tokens

Output

$4.05/ 1M tokens

Cache read

$0.170/ 1M tokens

Try it

Chat with InklingTerramind 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("inkling"),
  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 Thinking Machines

Model	Context	In	Out	Capabilities
thinkingmachines/inkling-small	1M	$0.450	$1.20	reasoningvisioncaching