Models
Inkling 2 Small (free)
Compare
Thinkingmachines logo

Inkling 2 Small (free)

inkling-2-small-freellms.txt
Thinkingmachines
New
Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model developed by Thinking Machines Lab. Featuring 17 billion active parameters out of a total of 594 billion, this model delivers powerful reasoning capabilities for complex tasks. With an expansive context window of 1,048,576 tokens, it is highly capable of processing and understanding massive amounts of multimodal data.
This model was retired on 2026-11-13.
Requests return 404 model_retired. All model retirements

Pricing

  • Input Tokens: $0 /M tokens
  • Output Tokens: $0 /M tokens
  • Cache Read: $0 /M tokens

Input Modalities

  • Text
  • Vision

Output Modalities

  • Text

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="inkling-2-small-free",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

Frequently asked questions

What is Inkling 2 Small (free)?

Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model developed by Thinking Machines Lab. Featuring 17 billion active parameters out of a total of 594 billion, this model delivers powerful reasoning capabilities for complex tasks. With an expansive context window of 1,048,576 tokens, it is highly capable of processing and understanding massive amounts of multimodal data.

© 2023 - 2026 AIHubMix, LLC

Product

Developer

Company

Terms & Policies