Xinference Pricing
At a glance
Xinference Community is free to self-host under Apache-2.0, with infrastructure and operating costs paid by the user. Xinference also offers a commercial OpenAI-compatible Model API billed per token, including DeepSeek and Kimi K3, plus managed dedicated-GPU inference and private enterprise deployments. Current API rates and dedicated deployment pricing require contacting sales. Official pricing checked October 15, 2026: https://xinference.co/pricing.html
Self-hosting cost
Xinference is open source under the Apache-2.0 license. Self-hosting does not add a software license fee, but you still pay for infrastructure, operations, and any external model or API usage.
Free & cheaper Model Providers
same category, free plan or open-source license
FAQ
How much does Xinference cost?
Xinference Community is free to self-host under Apache-2.0, with infrastructure and operating costs paid by the user. Xinference also offers a commercial OpenAI-compatible Model API billed per token, including DeepSeek and Kimi K3, plus managed dedicated-GPU inference and private enterprise deployments. Current API rates and dedicated deployment pricing require contacting sales. Official pricing checked October 15, 2026: https://xinference.co/pricing.html
Does Xinference have a free plan?
Yes — Xinference is open source and free to use.
Can you self-host Xinference for free?
Xinference is open source under the Apache-2.0 license. Self-hosting does not add a software license fee, but you still pay for infrastructure, operations, and any external model or API usage.
What are free or cheaper Xinference alternatives?
Claude, Cerebras, ChatGPT are in the same category with a free plan or open-source license.
pricing is editorial catalog data (last verified September 6, 2026) — vendors change plans; confirm on the official site before you buy. Reuse this data under CC-BY 4.0 via /data.
Community / applied corrections
- Incorrect information: @sue99955 · applied
Also sells paid plans: a Model API (DeepSeek and Kimi K3, OpenAI-compatible, billed per token) and dedicated inference on dedicated GPUs for enterprises.