免費 / 開源由 DeepSeek-V4 與 R1 驅動的高效開源權重與託管推理 AI,token 成本極低。
Lamini 每月有 4,158 次造訪,月增率 +0.3%,定價模式為免費增值、需聯絡報價。RightNow Inference(RunInfra)每月有 18,110 次造訪,成長率 -22.6%,定價模式為免費試用、付費、需聯絡報價。

Lamini is an enterprise LLM platform for building, fine-tuning, controlling and deploying custom large language models. It targets teams that need their own accurate, private models rather than a generic API: you bring your data, fine-tune open models on the platform, and serve them with tuned runtimes designed to reduce hallucinations. It covers use cases like text-to-SQL, classification, RAG and function calling, and is known for running workloads on AMD GPUs.
| 面向/指標 | ![]() | ![]() |
|---|---|---|
| 官方網域 | lamini.ai | runinfra.ai |
| 定價模式 | 免費增值、需聯絡報價 | 免費試用、付費、需聯絡報價 |
| 每月造訪次數 | 4158 (4,158) | 1.81萬 (18,110) |
| 月流量變化量 | +12 (+0.3%) | -5280 (-22.6%) |
| 主要市場與市佔 | 🇺🇸 美國 (92.9%) | 🇮🇳 印度 (48.4%) |
| 每月直接造訪 | 1637 | 7781 |
| 使用者評分 | 4.3 | 4.4 |
| 支援平台 | 網站 | 網站 |

Lamini is an enterprise LLM platform for building, fine-tuning, controlling and deploying custom large language models. It targets teams that need their own accurate, private models rather than a generic API: you bring your data, fine-tune open models on the platform, and serve them with tuned runtimes designed to reduce hallucinations. It covers use cases like text-to-SQL, classification, RAG and function calling, and is known for running workloads on AMD GPUs.
Train and fine-tune open large language models on your own domain data so output matches your vocabulary, formats and policies.
Tuned inference runtimes and grounding techniques aimed at cutting hallucinations and raising accuracy on domain-specific tasks.
Supports common enterprise patterns — retrieval-augmented generation, text-to-SQL, text classification and function calling.
Run training and inference workloads on AMD GPUs as an alternative GPU supply path for LLM workloads.

為代理快速提供開源模型推論,搭配熱快取路由
自動讓同一代理工作階段的重複呼叫落在已持有其上下文的副本上,快取命中率可報導達約 99%,明顯降低有效輸入成本。
一把 API 金鑰同時適用於 OpenAI 與 Anthropic SDK,現有代理程式碼只需極少修改即可切換服務商。
提供具公開定價的開源模型,支援工具呼叫、JSON 模式、串流輸出與影像輸入,並公布即時輸出速度與快取指標。
快取命中會顯示在用量中並依快取費率計費,同時公開測量方法與各模型的有效輸入價格。
免費 / 開源由 DeepSeek-V4 與 R1 驅動的高效開源權重與託管推理 AI,token 成本極低。
免費 / 開源在本機或雲端執行與打造開源 AI 模型

Together AI is the AI Native Cloud — a full-stack platform for running, fine-tuning and training open-source models. It spans serverless inference APIs, dedicated endpoints, GPU clusters, post-training and storage, all backed by in-house systems research.
Together AI is the AI Native Cloud — a full-stack platform for running, fine-tuning and training open-source models. It spans serverless inference APIs, dedicated endpoints, GPU clusters, post-training and storage, all backed by in-house systems research.
OrcaRouter is an OpenAI-compatible AI gateway that grades every prompt and routes it to the best-value model, then layers on failover, guardrails, an agent firewall, and compliance tooling for production AI.
OrcaRouter is an OpenAI-compatible AI gateway that grades every prompt and routes it to the best-value model, then layers on failover, guardrails, an agent firewall, and compliance tooling for production AI.
專項更強高可信前沿推論,端到端加密
專項更強Scale is an enterprise AI company that supplies the data, evaluation and deployment layers behind production AI. Its Data Engine sources and labels training data for frontier models, its evaluation work benchmarks model capability, and its platform teams help enterprises and governments move AI systems from pilot into real operations.
專項更強Scale is an enterprise AI company that supplies the data, evaluation and deployment layers behind production AI. Its Data Engine sources and labels training data for frontier models, its evaluation work benchmarks model capability, and its platform teams help enterprises and governments move AI systems from pilot into real operations.

專項更強不受限、相容 OpenAI 的 LLM API,由你自己的政策治理
專項更強不受限、相容 OpenAI 的 LLM API,由你自己的政策治理
用一個 API 快速、可預測成本地執行 LLM 與多模態模型