Xinference / Service profile
Model API · Australia
AU processing unverifiedA self-service, OpenAI-compatible API advertised as running in Australian data centres, with named DeepSeek and GLM models.
Source review: 09 Nov 2026 · Exact model configuration not yet verified
Model coverage
DeepSeek V4.1 Flash and GLM-5.3; names and prices should be checked against the live rate feed
API access
Self-service advertised
Billing
Per-token. Model API page lists $0.30/$1.20 DeepSeek V4.1 Flash and $1.40/$4.40 GLM-5.3 per 1M; currency not labelled.
Capacity commitment
Not yet verified.
Storage
Australian hosting advertised; storage categories not yet verified.
Retention and training
Provider says it does not train on prompts/outputs. Request logs are inspectable; prompt/output retention periods and subprocessors are not published on the reviewed Model API page.
Ownership and control
Australian processing and no-training statements are provider claims; reviewed public pages do not establish legal contracting entity, subprocessors, or failover destinations.
What to check before using it
- Confirm you are purchasing the shared Model API.
- Confirm the exact model and Australian processing boundary.
- Review retention and minimum payment requirements.
Still to verify
- Service-specific terms and subprocessors
- Routing and failover destinations
- Current live price feed and billing currency
Sources and supported claims
Model API and published rates ↗
The provider advertises Australian-hosted DeepSeek V4.1 Flash ($0.30 input / $1.20 output) and GLM-5.3 ($1.40 / $4.40) per 1M tokens. The page does not clearly state currency; rates are self-reported and can change.
Checked 2026-11-09 · Scope: this service profileModel API processing statement ↗
The provider says prompts and outputs are processed in Australian data centres and are not used for training absent written agreement.
Checked 2026-11-09 · Scope: this service profile