Inkling Small API

thinkingmachines/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 — the smaller, more efficient member of the Inkling family.
Context
524K tokens
Input
$0.797732 / 1M tokens
Output
$1.980576 / 1M tokens
Released
Jul 30, 2026

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.

Inkling Small API Pricing

TypePrice
Input
$0.797732 / 1M tokens
Output
$1.980576 / 1M tokens
Cached input
$0.1595464 / 1M tokens

Cached input billed at $0.1508 / 1M tokens.

Inkling Small Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
Intelligence
26.1
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Coding
52.9
Composite score across standardised coding evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

Inkling Small vs other models

ModelInputOutputContextBest for
Inkling Small
This page
$0.797732 / 1M tokens
$1.980576 / 1M tokens
524K tokens
Efficient open-weight multimodal reasoning
$0.6877 / 1M tokens
$2.95711 / 1M tokens
128K tokens
Chat + assistants
$2.0631 / 1M tokens
$10.3155 / 1M tokens
262K tokens
Reasoning + agents
$0.20631 / 1M
$0.6877 / 1M
66K tokens
Reasoning + agents
$0.34385 / 1M tokens
$2.7508 / 1M tokens
262K tokens
Reasoning + agents

Frequently asked questions

Inkling Small has a 524,288 tokens context window and can return up to 262,144 tokens.

Inkling Small takes image, text as input and returns text.

Use thinkingmachines/inkling-small as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

Inkling Small became available on July 30, 2026.

Inkling Small is priced at input $0.797732 / 1M tokens, output $1.980576 / 1M tokens, cached input $0.1595464 / 1M tokens.

Yes, Inkling Small can stream responses as they are generated.

Yes, Inkling Small accepts image input alongside text.

Inkling Small was built by Thinking Machines.

Start building with Inkling Small

Get API Key
1000+ models, one API.