Name: Inkling Small API
Brand: Thinking Machines

Overview

What is Inkling Small?

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family, accepting text and image input and returning text.

API Pricing

Input: $0.754 / 1M tokens
Cached input: $0.1508 / 1M tokens
Output: $1.872 / 1M tokens

Released July 30, 2026.

Uptime and performance

Uptime (7d): 100%

Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.

Use cases

Thinking Machines documents Inkling-Small as suited for building agentic and tool-use systems, including tasks where the model needs to act on tools while reasoning. It is also documented for coding assistants, with support for multiple coding languages and use in developer-facing coding workflows.

The model is documented as suitable for chatbots and general-purpose conversational use, including instruction-following and other natural language tasks. It is also described for retrieval-augmented generation systems, where it can support applications that combine retrieved information with model responses.

How to use Inkling Small API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to thinkingmachines/inkling-small.

import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "thinkingmachines/inkling-small",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())

const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "thinkingmachines/inkling-small",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());

curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"thinkingmachines/inkling-small","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.