Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for thinkingmachines

thinkingmachines

Access 6 thinkingmachines models through the OpenRouter unified API including Inkling Small, Inkling Small (free), and Inkling Small (batch). Compare pricing, context windows, benchmarks, and capabilities between different thinkingmachines models.

thinkingmachines tokens processed on OpenRouter

  • Favicon for thinkingmachines
    Thinking Machines: Inkling SmallInkling Small
    8.26B tokens

    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 and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.

    by thinkingmachinesJul 30, 20261.05M context$0.45/M input tokens$1.20/M output tokens
  • Favicon for thinkingmachines
    Thinking Machines: Inkling Small (free)Inkling Small (free)Free variant
    138B tokens

    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 and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.

    by thinkingmachinesJul 30, 20261.05M context$0/M input tokens$0/M output tokens
  • Favicon for thinkingmachines
    Thinking Machines: Inkling Small (batch)Inkling Small (batch)Batch variant
    771K tokens

    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 and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.

    by thinkingmachinesJul 30, 2026524K context$0.50/M input tokens$1.20/M output tokens
  • Favicon for thinkingmachines
    Thinking Machines: InklingInkling
    35.3B tokens

    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, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.

    by thinkingmachinesJul 17, 20261.05M context$0.95/M input tokens$4.05/M output tokens
  • Favicon for thinkingmachines
    Thinking Machines: Inkling (free)Inkling (free)Free variant
    419B tokens

    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, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.

    by thinkingmachinesJul 17, 20261.05M context$0/M input tokens$0/M output tokens
  • Favicon for thinkingmachines
    Thinking Machines: Inkling (batch)Inkling (batch)Batch variant
    942K tokens

    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, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.

    by thinkingmachinesJul 17, 2026524K context$1/M input tokens$4.05/M output tokens

Frequently asked questions

OpenRouter serves 6 thinkingmachines models behind one OpenAI-compatible API. Create an OpenRouter API key, point your client at https://openrouter.ai/api/v1, and set the model to an ID such as thinkingmachines/inkling-small. The quickstart has request examples for every supported SDK.

Inkling Small (free) and Inkling (free) are available at no cost through the OpenRouter API.

Inkling Small has the largest context window of any thinkingmachines model on OpenRouter, accepting up to 1,048,576 tokens per request.

Inkling Small is the most recently added thinkingmachines model on OpenRouter, listed on July 30, 2026.