Audience
Enterprise engineering and platform teams running AI in production
About Xinference
Xinference is a self-serve Model API for Kimi K3 and DeepSeek, hosted in Australia on dedicated GPUs. Developers and teams call both models through one OpenAI-compatible API, at the same per-token price as the model vendor. Switching from another OpenAI-compatible provider means changing the base URL and API key.
No prompt or response content kept by default, and no training on your data.
Don't see the model you need? Talk to us about adding it.
For teams that need models in their own environment, Xinference Dedicated Inference runs open models in your VPC, data centre or servers.
Xinference is in the process of becoming SOC 2 and ISO 27001 compliant.
Other Popular Alternatives & Related Software
Kimi K3
Kimi K3 is Moonshot AI’s most capable model, built for frontier intelligence scenarios such as software engineering, knowledge work, deep reasoning, and multimodal understanding. The model has 2.8 trillion parameters and uses Kimi Delta Attention, a hybrid linear attention mechanism, along with Attention Residuals for long-context performance. Kimi K3 supports a 1 million token context window, making it useful for analyzing large codebases, long documents, complex knowledge bases, and multi-step workflows. It includes native visual understanding for images and videos, with support for structured message formats, base64 image input, uploaded video files, and multimodal reasoning. Developers can use Kimi K3 through an OpenAI-compatible API with support for streaming, structured JSON output, partial mode, custom tools, dynamic tool loading, and automatic context caching.
Learn more about Kimi K3
Run BiOS
Run BiOS is serverless, OpenAI-compatible inference. Point the OpenAI SDK at the Run BiOS endpoint and keep your code. Six model families — Claude, DeepSeek, GLM, Kimi, MiniMax and Qwen — plus bios-adaptive, which routes each request for quality, speed and budget against a published price ceiling. Prompts and responses live in memory and are discarded when the request completes: no request logs, no content store, no archive. Fine-tuning and dedicated GPU endpoints run from the same account if you later want weights you own, billed per second of GPU time. Pricing is usage-based from a pre-paid balance, published per million tokens, and an endpoint pauses rather than running up a debt if the balance reaches zero.
Learn more about Run BiOS
OpenRouter
OpenRouter is an AI model routing platform that gives developers access to hundreds of models through a single unified API. It connects users with models from providers such as OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, Qwen, xAI, and many others. The platform supports text, image, video, and audio generation while allowing developers to use one API key and a consistent interface across providers. OpenRouter can route requests based on price, performance, and availability, with fallback options that help maintain service when a provider experiences downtime. It also offers configurable data policies so organizations can control which providers receive prompts and how requests are handled. Developers can purchase credits, choose from more than 500 active models across over 80 providers, and integrate OpenRouter using an OpenAI-compatible API.
Learn more about OpenRouter
Macyou
Macyou rents dedicated Apple Silicon Macs for AI workloads. Users configure a Mac (M4 Mac mini to Mac Studio M3 Ultra with 256 GB unified memory), pick a pre-configured stack — local LLMs via Ollama (Llama, Qwen, Mistral, DeepSeek), agent frameworks (CrewAI, LangGraph), or ML dev environments (MLX, Jupyter) — and get a running deployment in about 5 minutes. Every deployment exposes an OpenAI-compatible API, so existing OpenAI SDK code works by changing base_url; access also includes SSH with root and a browser-based remote desktop. Each customer gets a dedicated physical machine with full-disk encryption and a disk wipe between tenants, hosted in a GDPR-friendly jurisdiction. Pricing is a fixed monthly fee per machine with no per-token charges; Thunderbolt 5 clustering pools unified memory across nodes for larger models. Published, measured inference benchmarks (raw JSON, CC BY 4.0) show real tokens per second per chip.
Learn more about Macyou
Integrations
API:
Yes, Xinference offers API access
No integrations listed.
Company Information
Xinference
Founded: 2026
Australia
xinference.co
Videos and Screen Captures
Other Useful Business Software
Custom VMs From 1 to 96 vCPUs With 99.95% Uptime
Live migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
Product Details
Platforms Supported
Cloud
On-Premises
Training
Documentation
Xinference Frequently Asked Questions
Q: What kinds of users and organization types does Xinference work with?
Xinference works with these users and organization types: Mid Size Business, Small Business, Enterprise, Freelance, Nonprofit, Government, and Startup.
Q: What languages does Xinference support in their product?
Xinference supports these languages: English.
Q: Does Xinference have an API?
Yes, Xinference has an API.
Q: What type of training does Xinference provide?
Xinference provides training in the form of documentation.
