Enterprise DNAEnterprise DNA
LModelsBest vision
T

Inkling

by Thinkingmachines

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

I

Models

Inkling

Added 18 July 2026

#thinkingmachines

Overview

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,...

How to use / API access

Call via OpenRouter with model id `thinkingmachines/inkling`.

  • openrouter · thinkingmachines/inkling Docs

OpenRouter id: thinkingmachines/inkling

Benchmarks

  • Intelligence Index (artificial-analysis): 25 index
  • Coding Index (artificial-analysis): 52.1 index
  • Agentic Index (artificial-analysis): 22.5 index
  • Design Arena webapps (other): 1194 elo · #22
  • Design Arena 3d (other): 1162 elo · #63
  • Design Arena asciiart (other): 1094 elo · #62
  • Design Arena codecategories (other): 1207 elo · #56

Notes

Inkling is listed in the EDNA Models directory from the OpenRouter catalogue.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

USAGE / OPENROUTER

How much Inkling is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
284B ▼1.6%
Requests, last 7 days
4.7M
Tool calls, last 7 days
3.2M
Intelligence score
25
Average cost per request
$1.79
Price per million tokens
$1 in · $4.05 out
050B100B19 Sept: 50B tokens, 741K requests20 Sept: 61.1B tokens, 797K requests21 Sept: 58B tokens, 902K requests22 Sept: 48.7B tokens, 799K requests23 Sept: 43.4B tokens, 698K requests24 Sept: 47.1B tokens, 703K requests25 Sept: 42.3B tokens, 642K requests26 Sept: 40.9B tokens, 618K requests27 Sept: 38.6B tokens, 558K requests28 Sept: 41.2B tokens, 672K requests29 Sept: 33B tokens, 573K requests30 Sept: 35.6B tokens, 601K requests1 Oct: 37.2B tokens, 613K requests2 Oct: 33.8B tokens, 580K requests3 Oct: 32.2B tokens, 559K requests4 Oct: 30.1B tokens, 528K requests5 Oct: 38.3B tokens, 643K requests6 Oct: 52.2B tokens, 958K requests7 Oct: 46B tokens, 820K requests8 Oct: 42.3B tokens, 711K requests9 Oct: 41.4B tokens, 725K requests10 Oct: 36.7B tokens, 607K requests11 Oct: 39.5B tokens, 676K requests12 Oct: 43.1B tokens, 766K requests13 Oct: 43.4B tokens, 740K requests14 Oct: 42.4B tokens, 719K requests15 Oct: 40.4B tokens, 654K requests16 Oct: 40B tokens, 653K requests17 Oct: 43.1B tokens, 672K requests18 Oct: 41.7B tokens, 659K requests19 Oct: 40.6B tokens, 685K requests20 Oct: 40.6B tokens, 696K requests21 Oct: 37.7B tokens, 631K requests19 Sept3 Oct17 Oct21 OctSee where it ranks on the leaderboard →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Check the source

Price date: 2026-10-18. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 25 (2026-10-18) ↗Coding Index: 52.1 (2026-10-18) ↗Agentic Index: 22.5 (2026-10-18) ↗
Compare this model with alternatives →