Hosted in Australia
Sovereign inference.
Run any model. One API.
DeepSeek and GLM through one OpenAI-compatible API, hosted in Australia. Any other open model on request.
client = OpenAI(
base_url=XINFERENCE_BASE_URL,
api_key="XINFERENCE_API_KEY",
)
# two lines. that's the migration.
# paste into Claude Code, Cursor or Codex
Use the Xinference Model API in this project.
It is OpenAI-compatible. Set base_url to
https://cloud.xinference.co/v1 and api_key to XINFERENCE_API_KEY,
then call the model deepseek-v4.1-flash or glm-5.3.
Trusted in production by
Pay per token.
Same per-token price as the model vendor, hosted in Australia. Create an account, get your key and pay only for the tokens you use.

DeepSeek V4.1 Flash
Long-context work and RAG
$0.30 in $1.20 out
Hosted in Australia

GLM-5.3
Agents, reasoning and coding
$1.40 in $4.40 out
Hosted in Australia

Kimi K3
Frontier reasoning and agents
Coming soon
Hosted in Australia
300+ more open models
Qwen, Llama, Gemma, Mistral and more, on request.
Talk to us about adding one →
Price per 1M tokens. DeepSeek V4.1 Flash costs up to 53% less than DeepSeek on Amazon Bedrock in Sydney and up to 88% less per token than Claude Sonnet 5.5. List prices as of October 2026.
Works in the tools you already use
Set up DeepSeek or GLM in Hermes, DeepSeek Harness, n8n and more. Each guide takes a base URL, a key and a model name.
Australian hosting at the vendor’s price
No region surcharge. DeepSeek and GLM are hosted in Australia for the same per-token price the model vendor charges.
- No training on your data.
- In the process of becoming SOC 2 and ISO 27001 compliant.
- Security details in our Trust centre.
DeepSeek V4.1 Flashper 1M tokensWhy teams switch
Most teams start on the Model API and move to dedicated compute as usage grows.
See customer results→No lock-in
Open models behind one OpenAI-compatible API. Swap models, hardware or clouds without rebuilding your applications.
Cost certainty
Published prices per token. Pay for what you use, and move to a set cost per GPU hour as you grow.
Hosted in Australia
Runs in Australian data centres. No training on your data.
Start in minutes
Sign up, create a key and change two lines of code. No sales call needed.
In production.
Transport and logisticsCode review moved off a closed model.
Every push into main is reviewed on DeepSeek V4.1 Flash through the Model API, and a posted review is a required check before merging.
Health softwareSmart models for the hard calls, light models for the rest.
Ads analysis goes to a reasoning model and routine drafts to a faster, cheaper one, behind one API.
Training softwareA website chatbot that doesn’t need the most expensive model.
Visitors get answers from Cloud Assess’s own content, on a fast, low-cost model.
What you can build on Xinference.
Most production workloads already run on open models, with the same or similar results as closed-source APIs.
Search and RAG
Answer questions over your own documents.
Conversational AI
Customer assistants and internal helpdesks.
Agents and function calling
Multi-step reasoning and tool use, on frontier open models such as DeepSeek V4.1 Flash and GLM-5.3. You can also build them with TobyBot, which runs bots on your own models.
Coding assistance
IDE copilots and code generation, on long-context models served with streaming.
Summarisation and extraction
Document parsing, summarisation and classification, including high-volume batch pipelines.
Long-context work
Contracts, reports and codebases in a single request.












