AnyLanguageModel 1.0
AnyLanguageModel 1.0 is a Swift API compatible with Apple's Foundation Models API that lets developers choose among system, open-weight, and hosted models. It supports tool calling, guided generation, image prompts, multiple inference providers, and Linux.
What it does
Developers can use it to build Swift apps that switch between on-device and hosted models through a shared API.
- Availability
- Available as version 1.0; GitHub repository and Swift Package Manager instructions provided
- Pricing model
- Not established
- Deployment
- Local models on Apple platforms and Linux; hosted providers also supported
- Privacy
- API keys can be fetched as short-lived tokens from an app's server
- Licence
- Not established
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
5 claims- Tool calling and guided generation work with every provider. [1]
Tool calling works with every provider.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - Image prompts are supported, including with the system model on iOS, macOS, and visionOS 27. [1]
including when you use the system model on iOS, macOS, and visionOS 27.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - Supported providers include OpenAI APIs, Anthropic Messages API, Google's Gemini API, Ollama, and Hugging Face Inference Providers. [1]
- AnyLanguageModel runs on Linux as well as Apple platforms. [1]
AnyLanguageModel also runs on Linux,
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - AnyLanguageModel 1.0 is available from the GitHub repository and can be added as a Swift Package Manager dependency. [1]
Sources
1
1
Hugging FaceOwner-controlled
https://huggingface.co/blog/anylanguagemodel-1-0
Retrieved 2026-10-28 00:27 UTC
Verified
Versions
7| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 7 | 2026-10-28 00:27 UTC | material change | capability, access, deployment, availability, deployment | Current |
| 6 | 2026-10-26 01:36 UTC | material change | access, availability, deployment | Current |
| 5 | 2026-10-25 01:21 UTC | material change | access, deployment, availability, deployment | Current |
| 4 | 2026-10-24 01:40 UTC | material change | modality, deployment, pricing, availability, deployment | Current |
| 3 | 2026-10-23 01:22 UTC | material change | capability, modality, deployment, pricing, availability, deployment | Current |
| 2 | 2026-10-22 00:40 UTC | material change | capability, modality, deployment, availability, deployment, privacy | Current |
| 1 | 2026-10-20 17:18 UTC | publication | None | Current |
In briefs
2- A toolkit for voice agents that listen, respond, and take action Weekly brief 2026-W43
- Voice agents can take actions during a live conversation Daily brief 2026-10-20
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.