Hormouz AIHormouzSign in

Thinking Machines: Inkling: AI model

Inkling is a large open-weight multimodal mixture-of-experts model from Thinking Machines with a 524K-token context window. Reachable from inside Iran through Hormouz.

Context window:
524,288 tokens
Input:
$1/1M tokens
Output:
$4.05/1M tokens
Type:
text, image, audio
  • Vision
  • Tools
  • Streaming
  • Long context

Thinking levels: max · high · medium · low · minimal · none

Inkling is Thinking Machines Lab's open-weight model: a 975B mixture-of-experts with 41B active parameters. It is built for general reasoning, coding, agent and tool-use systems, retrieval-augmented answers, careful instruction following and multilingual conversation, and it understands images and audio natively alongside text.

It accepts text, image and audio input and returns text, and supports tool calling and streaming. Reasoning can be switched on when a problem needs more thought and left off when speed matters. Inkling is commonly used for general assistants, retrieval-augmented question answering, coding, tool-using agents and audio or image analysis. Hormouz serves it behind an OpenAI-compatible API: point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs without changes.

Pricing is usage-based: $0.95 per million input tokens and $4.05 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "thinkingmachines/inkling",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorThinking Machines
TypeText, Image, Audio
Context window524,288 tokens
Pricing$1.00/M in · $4.05/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Benchmarks

25
Intelligence Index
Better than 47% of models we compared
52.1
Coding Index
Better than 57% of models we compared
22.5
Agentic Index
Better than 53% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
87.2%
HLE
Humanity's Last Exam
31.9%
AA-LCR
Long-context reasoning
77.3%
CritPt
Research-level physics reasoning
5.4%
AA Omniscience
Broad factual knowledge accuracy
41.5%
Non-Hallucination
Rate of avoiding fabricated answers
32.3%

Coding

SciCode
Python for scientific computing
47%

Agentic

GDPval
Economically valuable tasks
28.9%

Source: Artificial Analysis

Design Arena

How Design Arena works ↗
3D
Top 44%
1,171Elo
Win rate: 40.4%Avg time: 56.3s
ASCII Art
Top 87%
1,102Elo
Win rate: 33.7%Avg time: 95.0s
Code
Top 37%
1,210Elo
Win rate: 42.1%Avg time: 84.3s
Data Viz
Top 55%
1,174Elo
Win rate: 38.1%Avg time: 74.7s
Game Dev
Top 48%
1,177Elo
Win rate: 37.9%Avg time: 92.4s
SVG
Top 62%
1,114Elo
Win rate: 34.1%Avg time: 25.4s
UI Component
Top 41%
1,205Elo
Win rate: 41.1%Avg time: 65.4s
Website
Top 33%
1,229Elo
Win rate: 44.3%Avg time: 90.9s

Metrics sourced from Design Arena

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "thinkingmachines/inkling",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="thinkingmachines/inkling",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "thinkingmachines/inkling",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Thinking Machines: Inkling API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Thinking Machines: Inkling and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Inkling cost?
Pricing is usage-based: $0.95 per million input tokens and $4.05 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use.
How do I access Inkling from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Is Inkling compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Point your base URL at Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
What context window and capabilities does Inkling have?
It has a 524K-token context window, accepts text, image and audio input, and supports tool calling and streaming. Reasoning can be switched on when a problem needs more thought and left off when speed matters.
What is Inkling good for?
Typical uses are general assistants, retrieval-augmented question answering, coding, tool-using agents and audio or image analysis.

Updated 2026-10-13