Inkling Small

• GPQA DiamondVery hard multiple-choice questions in biology, physics and chemistry, written by PhD experts. Random guessing scores 25%.88.5%#36 of 116
• AIME mathCompetition-level math problems in the style of the American Invitational Mathematics Examination. Share solved.90.0%#41 of 112
• FrontierMathOriginal, unpublished math problems written by professional mathematicians, from advanced to research level. Share solved.46.3%#43 of 73
• SimpleQA VerifiedShort factual questions. Measures how often the model gets facts right instead of making something up.19.1%#60 of 69

Benchmark data: Epoch AI, licensed CC BY 4.0

Companies that serve this model through an API: 1. Prices per million tokens, cheapest first.

Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.

Call Inkling Small through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "thinkingmachines/inkling-small", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'

import os
from openai import OpenAI

client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key=os.environ["OPENROUTER_API_KEY"])
reply = client.chat.completions.create(
    model="thinkingmachines/inkling-small",
    messages=[{"role": "user", "content": "Hello! What can you do?"}],
)
print(reply.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://openrouter.ai/api/v1", apiKey: process.env.OPENROUTER_API_KEY });
const reply = await client.chat.completions.create({
  model: "thinkingmachines/inkling-small",
  messages: [{ role: "user", content: "Hello! What can you do?" }],
});
console.log(reply.choices[0].message.content);

The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.

• 1,000 chat replies

  ≈ 500 tokens in, 300 out each
  $0.585
• Summarise a 100-page document

  ≈ 50,000 tokens in, 1,000 out
  $0.024
• An app with 10,000 requests a day for a month

  ≈ 1,000 tokens in, 400 out each
  $279

Cost calculator →

How much does Inkling Small cost?

Inkling Small costs $0.45 per million input tokens and $1.20 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $0.585.

What is the context window of Inkling Small?

Inkling Small can read up to 524,288 tokens in one request, about 983 pages of text. It can write up to 262,144 tokens in a single answer.

Is Inkling Small open source?

Yes. Its weights are published (thinkingmachines/Inkling-Small), so you can download it and run it on your own hardware, or use it through one of 1 API providers.

Who makes Inkling Small?

Inkling Small is made by Thinking Machines Lab. It became available through the API on July 30, 2026.

How good is Inkling Small?

Inkling Small has an overall index of 150.1 in Epoch AI’s independent tests, ranking #43 of 136 models we track.

Can Inkling Small read images?

Yes. Besides text, it accepts images and audio as input.

What are the alternatives to Inkling Small?

Models with a similar price from other companies include MiMo-V2.6-Pro, Qwen3.8 27B and Seed 2.1 Turbo. You can compare them side by side on this page.