Free (rate-limited)
Inkling 2 Small is free on OpenRouter and OpenCode Zen
Inkling 2 Small is free for a limited time on OpenRouter and OpenCode Zen, with about 1 million tokens of context
Thinking Machines Lab’s Inkling 2 Small now has free routes on OpenRouter and OpenCode Zen, with no charge for input or output. It offers about 1 million tokens of context and is a good fit for coding agents and longer tasks. The OpenRouter free endpoint is rate-limited; the OpenCode route has to be used inside OpenCode. No end date has been announced.
- Eligibility
- An OpenRouter account can call the :free route; the OpenCode free tier has to be used inside OpenCode. The OpenCode route is not available in the EU, Iceland, Liechtenstein, Norway, Cuba, Iran, North Korea, Russia, Ukraine, or Venezuela. The free routes may retain request content to improve the model, so do not upload confidential or personal data.
- Benefit duration
- Free for a limited time; no end date has been announced
The briefing
Thinking Machines Lab’s Inkling 2 Small now has free routes on OpenRouter and OpenCode Zen, with no charge for input or output. It is the first model in the second Inkling generation: an open-weight mixture-of-experts model with about 594 billion total parameters and 17 billion active per token. It reads text and images, with about 1 million tokens of context, and is suited to coding agents, autonomous research, and longer knowledge work.
What you get
The OpenRouter model ID is thinkingmachines/inkling-2-small:free. The free endpoint allows up to 20 requests per minute. Accounts that have purchased fewer than 10 credits get up to 50 requests per day; after at least 10 credits have been purchased, the daily cap rises to 1,000. Completions are capped at about 131,000 tokens, and the route supports tool use and reasoning.
The OpenCode Zen model ID is inkling-2-small-free. Input, output, and cache writes are free. Free chat models have to be called from inside OpenCode.
No end date has been announced. The same model on Vercel AI Gateway is pay-per-use at $0.30 per million input tokens and $1.00 per million output tokens, with no complimentary credit. Thinking Machines’ own API is also billed by usage.
The OpenRouter free route is meant for agentic harnesses. Prompts and outputs are logged to improve Thinking Machines Lab’s models and services, so do not upload confidential information, or personal data such as faces or voices.
The OpenCode route may also retain data for training. It is not available in the EU, Iceland, Liechtenstein, Norway, Cuba, Iran, North Korea, Russia, Ukraine, or Venezuela.
How to use it
- Create an OpenRouter API key, set the Base URL to
https://openrouter.ai/api/v1, and use the model namethinkingmachines/inkling-2-small:free. - Open OpenCode, sign in, and switch to Inkling 2 Small Free with
/models, or set the model toopencode/inkling-2-small-freein your config.
See the OpenRouter model page, the OpenRouter free-endpoint limits, and the OpenCode model docs.
