Now live: DeepSeek V4.1 Flash and GLM-5.3, hosted in Australia. Get started →

Customers

Teams building on Xinference.

From AI-native startups to enterprises with thousands of staff. See what they run and what changed.

Get started Talk to experts

AI-native companies

AI-native teams shipping models and agents.

Model API and agents on one stack, from code review to warehouse operations.

TransVirtualModel APITransport and logistics

Moved code review off a closed model. Every push now reviewed in about 10 seconds.

TransVirtual moved its pull request reviews off a closed-model API. Every push into main is now reviewed on DeepSeek V4.1 Flash through Xinference Model API, and a posted review is a required check before merging.

Up to 88% less costper token than Claude Sonnet 5.5, at list prices
~240 tokens/soutput speed on DeepSeek V4.1 Flash
Read the story →
~10 secper pull request review
Model APIOpenAI-compatible. DeepSeek V4.1 Flash and GLM-5.3, pay per token. Point your client at Xinference and keep your code.
POST /v1/chat/completions
client = OpenAI(
    base_url=XINFERENCE_BASE_URL,
    api_key="XINFERENCE_API_KEY",
)

# two lines. that's the migration.

More AI-native teams

Enterprise

Enterprises running their AI on one platform.

Dedicated deployments, with the numbers each team reported.

6,000staff on one pooled clusterFinancial services
1.52Mrequests a day across dual data centresYum! Brands
500K+requests a day on one serving stackAIA
50+AI use cases on one shared clusterYum! Brands
Siemens
Manufacturing
Xinference gives us one platform to run every model on infrastructure we fully control.
Marcus Z., Senior AI Infrastructure Lead, Siemens
TFC OpticalComms
Optical communications
We consolidated model serving onto Xinference and stopped babysitting the stack ourselves.
Jason L., VP of Engineering, TFC OpticalComms

What customers run

Common workloads on Xinference.

Document processing

Parsing, extraction and compliance checks across large document sets.

Financial services, Yum! Brands

Code review

A review on every push, posted as a required check.

TransVirtual

Support agents

Agents that answer customers and staff from your knowledge base.

ShiftCare, Cloud Assess

Lead follow-up

A brief on every new lead, in Slack, within minutes.

Detrack

Operations agents

Stock monitoring, cycle counts and reordering in the warehouse.

Datapel

Model routing

Reasoning models for hard calls, fast models for the rest.

Personify Care, Cloud Assess

Trusted in production by

TransVirtual ShiftCare Datapel Detrack Personify Care Cloud Assess Siemens Yum! Brands Financial services customer AIA TFC OpticalComms

Run the numbers on your workload.

A cost assessment takes one call. The savings model is yours to keep.