Thinking Machines Lab

Inkling

MoEotherReleased Jul 2026

Thinking Machines Lab's open-weights general-purpose multimodal Mixture-of-Experts model with 975B total parameters and 41B active parameters. Inkling accepts text, image, and audio inputs, produces text, and is designed for agentic and tool-use systems, coding assistants, chatbots, and retrieval-augmented generation.

Capabilities

chatcompletionfunction-callingvisionaudiocode-generation

Modalities

textimageaudiocode

Context Window

1.0M tokens

Providers

available

Available from 1 provider

Cheapest

Tinker

$6.55/1M tokens

Tinker

Providers (1)

Sorted by total cost (input + output per 1M tokens). Click a row to view provider details.

Provider	Pricing (per 1M)	Rate Limits	Regions	Health	Latency
Tinker	In: $1.87Out: $4.68	60 RPM / 1.0M TPM	global	Healthy	0ms

Quick Start

Use this model via Tinker with an OpenAI-compatible SDK.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.tinker.com/v1",
  apiKey: process.env.TINKER_API_KEY,
});

const response = await client.chat.completions.create({
  model: "thinkingmachines/Inkling",
  messages: [
    { role: "user", content: "Hello!" }
  ],
});

console.log(response.choices[0].message.content);

Using Tinker API • OpenAI-compatible SDK