Model · Fireworks AI

Ember-1

fireworks/ember-1

Try in Agents

Fireworks' research-preview reasoning model built on Kimi K3 — coding and agents with about 40% fewer generated tokens

reasoningvisioncaching

Specs

Context

1.0M

Max output

33K

Provider

Fireworks AI

Input

$3.00/ 1M tokens

Output

$15.00/ 1M tokens

Cache read

$0.300/ 1M tokens

Try it

Chat with Ember-1Terramind 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("ember-1"),
  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