25
Intelligence Index
Above 74% of 51 other free models
Th
Thinking Machines: Inkling
Free allowance
Up to50requests / day
via OpenRouter · < $10 credits
- 20 requests / minute
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,...
- Input
- text
- image
- audio
- Output
- text
- Audio understanding
Providers
Available through 2 free providers. Use the model ID and API settings below to connect.
Vercel AI Gateway
VAVercel AI Gateway
* The provider match may differ from this model. Check its docs for details.
Benchmarks
Compare scores and explore results by category.
52.1
Coding Index
Above 69% of 39 other free models
22.5
Agentic Index
Above 69% of 33 other free models
Bars show scores from other free models on this site. The marker shows this model’s score. Comparisons include only models with a score for that index.
Scores from Artificial AnalysisFrequently asked questions
Free access, setup, and what to expect.
Inkling is available with up to 50 requests / day free through OpenRouter (< $10 credits). Additional limits apply at the same time: 20 requests / minute. Free allowances can change. Check the Inkling provider limits before you start.
To use Inkling, choose one of the listed Inkling API providers and follow the provider’s account and API-key setup guide. Copy the Inkling model ID and connection settings for your chosen provider into your app or API client. Model IDs can differ between providers. API requests go directly to the provider; Free Models is a comparison site.
Inkling accepts text, image, and audio as listed input formats. Listed output formats include text. Image or audio input support does not imply image or audio generation. Check the chosen provider’s Inkling documentation for supported file types and request formats.
Inkling has a listed context window of 524K tokens. Tokens are small pieces of content rather than a word count. Instructions, conversation history, and other inputs use context space, and the response also needs room. The maximum output length for Inkling may be smaller than the context window and can vary by provider.
Inkling has both reasoning and tool calling listed as supported capabilities. Reasoning enables additional processing for complex problems. Tool calling allows a model to request functions that your app executes. Check the chosen provider’s documentation for capability availability and setup.
Review the listed Inkling benchmark results to compare performance on measured tasks. Compare scores within the same benchmark: coding indexes, Elo ratings, and win rates measure different things. The index comparison charts include only scored free models listed on Free Models. Evaluate Inkling on examples from your own task alongside context size and provider limits.