ScaledThought
← All models

Thinking Machines

Inkling

Live · US + CAtextimageaudiovideoApache 2.0

Thinking Machines Lab's first open model, trained on 45T multimodal tokens and built to be fine-tuned.

Price per 1M tokens

Input

$1.00

Cached input

$0.17

Output

$4.05

Priced per model · Same in US and CA · Free tier included · Pricing

AA Index

25

#11 of 14
open models we serve

Specs

Model id
inkling
Weights released
Jul 15, 2026
Parameters
975B total · 41B active
Architecture
MoE
Context
1M tokens (1,000,000)
Input
text, image, audio, video
License
Apache 2.0
Regions
us, ca

Benchmarks

  • Artificial Analysis Intelligence Index25

Sources: huggingface.co · thinkingmachines.ai · techcrunch.com

Use it

Three lines of code, or zero.

OpenAI-compatible. Use the model id below, or auto to let the router decide when this model is worth it.

Quickstart→
import os
from openai import OpenAI

client = OpenAI(base_url=os.environ["ST_BASE_URL"], api_key=os.environ["ST_API_KEY"])
resp = client.chat.completions.create(
    model="inkling",
    messages=[{"role": "user", "content": "Hello"}],
)

Opens your agent with the prompt typed. You press Enter.