{"slug": "highreso-japan-request-to-be-listed-as-an-inference-provider", "title": "Highreso (Japan) — request to be listed as an Inference Provider", "summary": "Highreso Co., Ltd., a GPU cloud operator with data centers in Kagawa and Saga, Japan, has asked Hugging Face to list it as an Inference Provider on the Hub, offering an OpenAI-compatible chat completions API at https://api.highreso.ai/hf/v1 served on Highreso-owned NVIDIA B200 clusters in Japan. Highreso reports measured single-user speed of 108 to 149 tokens/s (p50) for zai-org/GLM-5.3 (FP8) at 4 to 8 concurrent users, with Qwen/Qwen3-8B initially and moonshotai/Kimi-K3 to follow, and says pull requests for huggingface.js (provider \"highreso\") and huggingface_hub are open. The company asked Hugging Face to enable its organization (highreso-jp, Team plan) server-side so it can register model mappings via /api/partners/highreso/models.", "body_md": "Subject: Highreso (Japan) — request to be listed as an Inference Provider\n\nHi Hugging Face Inference Providers team,\n\nI’m writing on behalf of Highreso Co., Ltd., a GPU cloud operator based in Japan (data centers in Kagawa and Saga). We would like to be listed as an Inference Provider on the Hub.\n\nWhat we offer: an OpenAI-compatible chat completions API at `https://api.highreso.ai/hf/v1` (streaming, tool calling, structured output), served on Highreso-owned NVIDIA B200 clusters located in Japan. All data stays in Japan. Initial models: zai-org/GLM-5.3 (FP8) and Qwen/Qwen3-8B, with moonshotai/Kimi-K3 to follow. Measured single-user speed on our B200 nodes: GLM-5.3 108 to 149 tokens/s (p50) at 4 to 8 concurrent users. We list at the standard provider prices shown on the Hub. We expose a per-request Inference-Id header, a billing endpoint (`POST /hf/v1/billing`) that returns cost in nano-USD per request ID, and pricing plus context_length on `/hf/v1/models`.\n\nStatus: PRs for huggingface.js (provider “highreso”) and huggingface_hub are open:\n\nHub organization: highreso-jp (Team plan). Company site: `highreso.jp`. Contact: [inference@highreso.co.jp](mailto:inference@highreso.co.jp)\n\nCould you enable our organization server-side so we can register model mappings via `/api/partners/highreso/models`? Happy to provide a test key for your validation runs.\n\nThank you,\n\nHighreso Co., Ltd.", "url": "https://wpnews.pro/news/highreso-japan-request-to-be-listed-as-an-inference-provider", "canonical_source": "https://discuss.huggingface.co/t/highreso-japan-request-to-be-listed-as-an-inference-provider/190926#post_1", "published_at": "2026-10-23 01:07:51+00:00", "updated_at": "2026-10-23 01:12:10.175291+00:00", "lang": "en", "topics": ["ai-infrastructure", "ai-chips", "large-language-models", "ai-products"], "entities": ["Highreso Co., Ltd.", "Hugging Face", "NVIDIA B200", "zai-org/GLM-5.3", "Qwen/Qwen3-8B", "moonshotai/Kimi-K3", "huggingface.js", "huggingface_hub"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/highreso-japan-request-to-be-listed-as-an-inference-provider", "markdown": "https://wpnews.pro/news/highreso-japan-request-to-be-listed-as-an-inference-provider.md", "text": "https://wpnews.pro/news/highreso-japan-request-to-be-listed-as-an-inference-provider.txt", "jsonld": "https://wpnews.pro/news/highreso-japan-request-to-be-listed-as-an-inference-provider.jsonld"}}