Filtering by: providers · clear filter
Runware is now available as an opt-in NanoGPT provider.
Its self-hosted routes for GLM 5.2, GLM 5.3, GLM 5.3 Flash, DeepSeek V4 Flash, and GPT OSS 120B are classified as Zero Data Retention. They support streaming, tool calling, reasoning, and prompt caching.
Runware is currently serving GLM 5.3 at up to 500 tokens per second.
Choose Runware through provider selection or pass X-Provider: runware in API requests.
Heabsy is now available for Qwen3.8 27B and Qwen3.8 27B Thinking.
Its dedicated GPU deployments in Italy and Norway offer EEA Zero Data Retention, in-memory processing, streaming, tool calling, structured output, and a 131K context window.
Choose Heabsy from provider selection, or pass X-Provider: heabsy in API requests.
Details:
Public Provider Pages are now live on NanoGPT.
Compare inference providers by available models, pricing, region, privacy classification, performance, prompt caching, and provider-pinned model IDs.
Explore the provider directory: