thinkingmachinesVision
Thinking Machines: Inkling
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...
Context
1M tokens
Input / 1M tokens
$1
Output / 1M tokens
$4.05
Benchmark
—
Pricing
Input tokens$1 per 1M tokens
Output tokens$4.05 per 1M tokens
Cache read$0.17 per 1M tokens
Technical details
Model IDthinkingmachines/inkling
Context window1M tokens
Input modalitiestext, image, audio
Output modalitiestext
TokenizerOther
Use with MegaBrain
import OpenAI from 'openai'
const client = new OpenAI({
baseURL: 'https://getmegabrain.com/api/gateway/v1',
apiKey: process.env.MEGABRAIN_API_KEY,
})
const response = await client.chat.completions.create({
model: 'thinkingmachines/inkling',
messages: [{ role: 'user', content: 'Hello!' }],
})Ready to use Thinking Machines: Inkling?
Get an API key and start making requests in minutes.
Get an API key