# ScitiX

> ScitiX documentation provides guides for Model Inference, GPU Cloud, and account management, helping developers connect to model APIs, manage GPU resources, and configure accounts and billing.

- [Model Inference](https://docs.scitix.ai/model-inference/get-started/model-inference-overview.md): Learn what ScitiX Model Inference provides, including OpenAI-compatible APIs, model access, usage management, and common AI application scenarios.
- [Model Selection & Playground](https://docs.scitix.ai/model-inference/get-started/model-selection-playground.md): Learn how to use Model Assistant, Models, and Playground to select models, review model details, and test responses before integrating the Model Inference API.
- [First API Call](https://docs.scitix.ai/model-inference/get-started/first-api-call.md): Make your first ScitiX Model Inference API call by creating an API key, choosing a model, and sending an OpenAI-compatible request.
- [Connect ScitiX Docs to AI](https://docs.scitix.ai/model-inference/get-started/connect-docs-to-ai.md): Learn how to use MCP, llms.txt, skill.md, and Markdown pages to let AI tools query Model Inference documentation.
- [Text Generation](https://docs.scitix.ai/model-inference/models/text-generation.md): Explore text generation models available through ScitiX Model Inference for chat, content generation, coding, and general-purpose AI tasks.
- [Reasoning](https://docs.scitix.ai/model-inference/models/reasoning.md): Explore reasoning models in ScitiX Model Inference for math, coding, logic, planning, and multi-step problem solving.
- [Vision and Multimodal](https://docs.scitix.ai/model-inference/models/vision-and-multimodal.md): Explore vision and multimodal models in ScitiX Model Inference for image understanding, visual question answering, and multimodal workflows.
- [Embedding](https://docs.scitix.ai/model-inference/models/embedding.md): Learn about embedding models in ScitiX Model Inference for semantic search, retrieval, reranking, and RAG applications.
- [Speech](https://docs.scitix.ai/model-inference/models/speech.md): Learn about speech model capabilities in ScitiX Model Inference for audio, voice, and speech-enabled AI applications.
- [Function Calling（Tool Calling）](https://docs.scitix.ai/model-inference/models/function-calling.md): Learn how function calling and tool calling work in ScitiX Model Inference for agents, structured actions, and tool-using applications.
- [Structured Output](https://docs.scitix.ai/model-inference/models/structured-output.md): Learn how to use structured output in ScitiX Model Inference to generate reliable JSON responses for application workflows.
- [Streaming](https://docs.scitix.ai/model-inference/models/streaming.md): Learn how streaming responses work in ScitiX Model Inference for low-latency chat, coding, and interactive AI applications.
- [Long Context](https://docs.scitix.ai/model-inference/models/long-context.md): Learn about long-context models in ScitiX Model Inference for processing large documents, long conversations, and codebases.
- [Prompt Caching](https://docs.scitix.ai/model-inference/models/prompt-caching.md): Learn how prompt caching can reduce latency and cost for repeated context in ScitiX Model Inference workloads.
- [Token Usage and Billing](https://docs.scitix.ai/model-inference/usage/billing.md): Understand token types, billing formulas, reasoning tokens, output tokens, and max_completion_tokens in ScitiX Model Inference.
- [View Usage](https://docs.scitix.ai/model-inference/usage/view-usage.md): Learn how to view ScitiX Model Inference request details, token usage, cost, and latency metrics.
- [View Metrics](https://docs.scitix.ai/model-inference/usage/view-metrics.md): Learn how to view aggregated metrics, usage trends, token distribution, and latency performance for ScitiX Model Inference.
- [API Keys](https://docs.scitix.ai/model-inference/usage/api-keys.md): Learn how to create, manage, and protect API keys for ScitiX Model Inference, including usage limits and access control basics.
- [Error Handling](https://docs.scitix.ai/model-inference/api/error-handling.md): Understand ScitiX Model Inference API error responses, status codes, request IDs, trace IDs, and retry guidance.
- [Integrations Overview](https://docs.scitix.ai/model-inference/integrations/overview.md): Browse ScitiX Model Inference integrations for coding agents, IDEs, chat clients, RAG tools, workflow platforms, and AI frameworks.
- [DeepSeek Harness](https://docs.scitix.ai/model-inference/integrations/deepseek-harness.md)
- [Claude Code](https://docs.scitix.ai/model-inference/integrations/claude-code.md): Learn how to configure the endpoint and API Key in Claude Code CLI and the VS Code extension, connect to the ScitiX endpoint, and use ScitiX models that support the Anthropic protocol for coding.
- [Codex](https://docs.scitix.ai/model-inference/integrations/codex.md): Learn how to configure Codex CLI and the VS Code extension to use ScitiX Model Inference through config.toml and a ScitiX API key.
- [OpenCode](https://docs.scitix.ai/model-inference/integrations/opencode.md): Learn how to configure OpenCode with ScitiX Model Inference for terminal and IDE-based AI coding workflows.
- [Qwen Code](https://docs.scitix.ai/model-inference/integrations/qwen-code.md): Learn how to configure Qwen Code with ScitiX Model Inference for command-line coding agent workflows using ScitiX models.
- [Aider](https://docs.scitix.ai/model-inference/integrations/aider.md): Learn how to connect Aider to ScitiX Model Inference for terminal-based AI pair programming and code editing workflows.
- [Goose](https://docs.scitix.ai/model-inference/integrations/goose.md): Learn how to connect Goose to ScitiX Model Inference so the open-source AI agent can use ScitiX models in coding workflows.
- [Crush](https://docs.scitix.ai/model-inference/integrations/crush.md): Learn how to connect Crush to ScitiX Model Inference so the terminal AI coding agent can use ScitiX model endpoints.
- [CC-Switch](https://docs.scitix.ai/model-inference/integrations/cc-switch.md): Learn how to configure CC-Switch with ScitiX Model Inference to switch provider settings for Claude Code and related coding tools.
- [Cline](https://docs.scitix.ai/model-inference/integrations/cline.md): Learn how to configure Cline with ScitiX Model Inference using an OpenAI-compatible provider, API key, Base URL, and model ID.
- [Cursor](https://docs.scitix.ai/model-inference/integrations/cursor.md): Learn how to configure Cursor with a custom ScitiX model, API key, and Base URL for AI-assisted coding.
- [Roo Code](https://docs.scitix.ai/model-inference/integrations/roo-code.md): Learn how to configure Roo Code with ScitiX Model Inference using an OpenAI-compatible provider, Base URL, API key, and model ID.
- [Kilo Code](https://docs.scitix.ai/model-inference/integrations/kilo-code.md): Learn how to configure Kilo Code with ScitiX Model Inference using an OpenAI-compatible provider, API key, Base URL, and model list.
- [TRAE](https://docs.scitix.ai/model-inference/integrations/trae.md): Learn how to configure TRAE with ScitiX Model Inference so its AI IDE and agent workflows can use ScitiX models.
- [Continue](https://docs.scitix.ai/model-inference/integrations/continue.md): Learn how to configure Continue with ScitiX Model Inference for AI coding assistance in VS Code, JetBrains, and CLI workflows.
- [Zed](https://docs.scitix.ai/model-inference/integrations/zed.md): Learn how to configure Zed with ScitiX Model Inference for AI-assisted coding through an OpenAI-compatible provider.
- [Cherry Studio](https://docs.scitix.ai/model-inference/integrations/cherry-studio.md): Learn how to configure Cherry Studio with ScitiX Model Inference so the desktop AI client can chat with ScitiX models.
- [LobeChat](https://docs.scitix.ai/model-inference/integrations/lobechat.md): Learn how to configure LobeChat with ScitiX Model Inference so the chat framework can use ScitiX models through an OpenAI provider.
- [Open WebUI](https://docs.scitix.ai/model-inference/integrations/open-webui.md): Learn how to connect Open WebUI to ScitiX Model Inference so a self-hosted chat interface can use ScitiX models.
- [NextChat](https://docs.scitix.ai/model-inference/integrations/nextchat.md): Learn how to connect NextChat to ScitiX Model Inference for lightweight web and desktop chat with ScitiX models.
- [Chatbox](https://docs.scitix.ai/model-inference/integrations/chatbox.md): Learn how to connect Chatbox to ScitiX Model Inference by configuring an OpenAI provider, API key, endpoint, and model.
- [LibreChat](https://docs.scitix.ai/model-inference/integrations/librechat.md): Learn how to connect LibreChat to ScitiX Model Inference so a self-hosted ChatGPT-style web UI can use ScitiX models.
- [RAGFlow](https://docs.scitix.ai/model-inference/integrations/ragflow.md): Learn how to configure RAGFlow with ScitiX Model Inference for document understanding, knowledge base chat, and RAG workflows.
- [AnythingLLM](https://docs.scitix.ai/model-inference/integrations/anythingllm.md): Learn how to configure AnythingLLM with the ScitiX Model Inference endpoint for workspace chat, document chat, and agent workflows.
- [FastGPT](https://docs.scitix.ai/model-inference/integrations/fastgpt.md): Learn how to configure FastGPT with ScitiX Model Inference for knowledge base chat and AI workflow applications.
- [DB-GPT](https://docs.scitix.ai/model-inference/integrations/db-gpt.md): Learn how to configure DB-GPT with ScitiX Model Inference for chat-to-data, agents, and RAG data applications.
- [wiseflow](https://docs.scitix.ai/model-inference/integrations/wiseflow.md): Learn how to configure LLM_API_BASE in wiseflow and use ScitiX models for information mining and intelligence aggregation tasks.
- [Obsidian Copilot](https://docs.scitix.ai/model-inference/integrations/obsidian-copilot.md): Learn how to configure Obsidian Copilot with ScitiX Model Inference for AI chat and commands inside an Obsidian vault.
- [Zotero](https://docs.scitix.ai/model-inference/integrations/zotero.md): Learn how to configure Zotero GPT with ScitiX Model Inference for AI-powered literature reading and question answering.
- [SiYuan](https://docs.scitix.ai/model-inference/integrations/siyuan.md): Learn how to configure SiYuan with ScitiX Model Inference for AI chat and knowledge management workflows.
- [Dify](https://docs.scitix.ai/model-inference/integrations/dify.md): Learn how to connect Dify to ScitiX Model Inference for chatbot, agent, and workflow applications through an OpenAI-compatible provider.
- [OpenClaw](https://docs.scitix.ai/model-inference/integrations/openclaw.md): Learn how to configure OpenClaw with ScitiX Model Inference for personal AI assistant workflows across messaging platforms.
- [Langflow](https://docs.scitix.ai/model-inference/integrations/langflow.md): Learn how to configure Langflow with ScitiX Model Inference to build visual LLM applications and agent flows.
- [Flowise](https://docs.scitix.ai/model-inference/integrations/flowise.md): Learn how to configure Flowise ChatOpenAI Custom nodes with ScitiX Model Inference for low-code LLM workflows.
- [n8n](https://docs.scitix.ai/model-inference/integrations/n8n.md): Learn how to configure n8n credentials and AI Agent nodes with ScitiX Model Inference for automated LLM workflows.
- [Deep Research](https://docs.scitix.ai/model-inference/integrations/deep-research.md): Learn how to configure Deep Research with ScitiX Model Inference using proxy mode and an OpenAI-compatible provider.
- [LangBot](https://docs.scitix.ai/model-inference/integrations/langbot.md): Learn how to add an OpenAI model provider in LangBot, set a custom request URL, and connect multi-platform messaging bots to ScitiX models.
- [Refly](https://docs.scitix.ai/model-inference/integrations/refly.md): Learn how to add an OpenAI-compatible provider in Refly, configure the Base URL, and use ScitiX models in AI workflow orchestration.
- [LangChain](https://docs.scitix.ai/model-inference/integrations/langchain.md): Learn how to use LangChain with ScitiX Model Inference by configuring ChatOpenAI with a custom base URL and model ID.
- [LlamaIndex](https://docs.scitix.ai/model-inference/integrations/llamaindex.md): Learn how to use LlamaIndex with ScitiX Model Inference for RAG, agents, and OpenAI-compatible model access.
- [Vercel AI SDK](https://docs.scitix.ai/model-inference/integrations/vercel-ai-sdk.md): Learn how to use Vercel AI SDK with ScitiX Model Inference to build TypeScript AI applications with an OpenAI-compatible provider.
- [Pydantic AI](https://docs.scitix.ai/model-inference/integrations/pydantic-ai.md): Learn how to use Pydantic AI with ScitiX Model Inference to build typed Python agents with tool calling support.
- [LiteLLM](https://docs.scitix.ai/model-inference/integrations/litellm.md): Learn how to use LiteLLM with ScitiX Model Inference to route OpenAI-style requests through a unified LLM API interface.
- [CrewAI](https://docs.scitix.ai/model-inference/integrations/crewai.md): Learn how to use CrewAI with ScitiX Model Inference to build and run role-based AI agent workflows through an OpenAI-compatible API.
- [AutoGen](https://docs.scitix.ai/model-inference/integrations/autogen.md): Learn how to use AutoGen with ScitiX Model Inference to build multi-agent applications through an OpenAI-compatible endpoint.
- [OpenManus](https://docs.scitix.ai/model-inference/integrations/openmanus.md): Learn how to connect OpenManus to ScitiX Model Inference for general-purpose agent workflows through an OpenAI-compatible model API.
- [LazyLLM](https://docs.scitix.ai/model-inference/integrations/lazyllm.md): Learn how to use LazyLLM OnlineChatModule with a custom OpenAI-compatible endpoint and build low-code LLM applications on ScitiX models.
- [Chat2Graph](https://docs.scitix.ai/model-inference/integrations/chat2graph.md): Learn how to configure Chat2Graph with LiteLLM environment variables and connect graph-native agent workflows to ScitiX Model Inference.
- [Immersive Translate](https://docs.scitix.ai/model-inference/integrations/immersive-translate.md): Learn how to configure Immersive Translate with ScitiX Model Inference for bilingual web, PDF, and EPUB translation workflows.
- [PDFMathTranslate Next](https://docs.scitix.ai/model-inference/integrations/pdfmathtranslate-next.md): Learn how to configure PDFMathTranslate Next with ScitiX Model Inference for layout-preserving PDF translation workflows.
- [GPU Cloud](https://docs.scitix.ai/gpu-cloud/get-started/gpu-cloud-overview.md)
- [Choose a GPU Service](https://docs.scitix.ai/gpu-cloud/get-started/product-selection.md)
- [Usage Process](https://docs.scitix.ai/gpu-cloud/get-started/usage-process.md)
- [Connect ScitiX Docs to AI](https://docs.scitix.ai/gpu-cloud/get-started/connect-docs-to-ai.md): Learn how to use MCP, llms.txt, skill.md, and Markdown pages to let AI tools query GPU Cloud documentation.
- [Create an Instance](https://docs.scitix.ai/gpu-cloud/instance/create-instance.md)
- [View Instances](https://docs.scitix.ai/gpu-cloud/instance/list-instances.md)
- [Start, Stop, and Restart Instances](https://docs.scitix.ai/gpu-cloud/instance/start-stop-restart-instance.md)
- [Batch Manage Instances](https://docs.scitix.ai/gpu-cloud/instance/batch-manage-instances.md)
- [Modify Instance File Storage](https://docs.scitix.ai/gpu-cloud/instance/modify-instance-file-storage.md)
- [Delete an Instance](https://docs.scitix.ai/gpu-cloud/instance/delete-instance.md)
- [Create a Cluster](https://docs.scitix.ai/gpu-cloud/cluster/create-kubernetes-cluster.md)
- [View Clusters](https://docs.scitix.ai/gpu-cloud/cluster/list-kubernetes-clusters.md)
- [Cluster Actions Overview](https://docs.scitix.ai/gpu-cloud/cluster/actions/cluster-actions-overview.md)
- [Cluster Details](https://docs.scitix.ai/gpu-cloud/cluster/actions/view-cluster-details.md)
- [Delete a Cluster](https://docs.scitix.ai/gpu-cloud/cluster/actions/delete-cluster.md)
- [More Actions](https://docs.scitix.ai/gpu-cloud/cluster/actions/allow-diagnose.md)
- [Manage Namespaces](https://docs.scitix.ai/gpu-cloud/cluster/manage-namespaces.md)
- [Manage Kubeconfig](https://docs.scitix.ai/gpu-cloud/cluster/manage-kubeconfig.md)
- [Create a Volume](https://docs.scitix.ai/gpu-cloud/cluster/volume/create-storage-volume.md)
- [View Volumes](https://docs.scitix.ai/gpu-cloud/cluster/volume/list-storage-volumes.md)
- [Mount a Volume](https://docs.scitix.ai/gpu-cloud/cluster/volume/mount-storage-volume-to-pod.md)
- [Delete a Volume](https://docs.scitix.ai/gpu-cloud/cluster/volume/release-storage-volume.md)
- [GPFS Overview](https://docs.scitix.ai/gpu-cloud/storage/gpfs-overview.md)
- [Create a GPFS File System](https://docs.scitix.ai/gpu-cloud/storage/create-gpfs-file-system.md)
- [Mount a GPFS File System](https://docs.scitix.ai/gpu-cloud/storage/mount-gpfs-file-system.md)
- [Scale Up or Scale Down a GPFS File System](https://docs.scitix.ai/gpu-cloud/storage/resize-gpfs-file-system.md)
- [Delete a GPFS File System](https://docs.scitix.ai/gpu-cloud/storage/delete-gpfs-file-system.md)
- [Object Storage Quick Start](https://docs.scitix.ai/gpu-cloud/storage/use-oss-object-storage.md)
- [CES Monitoring Dashboard](https://docs.scitix.ai/gpu-cloud/monitoring/ces-dashboard.md)
- [Grafana Dashboard](https://docs.scitix.ai/gpu-cloud/monitoring/grafana-dashboard.md)
- [Subscribe to Product Alerts](https://docs.scitix.ai/gpu-cloud/alarm/subscribe.md)
- [Configure Notification Channels](https://docs.scitix.ai/gpu-cloud/alarm/config.md)
- [Alert History](https://docs.scitix.ai/gpu-cloud/alarm/history.md)
- [Initialize an Account](https://docs.scitix.ai/account/account-management/initialize-account.md)
- [Billing Account](https://docs.scitix.ai/account/account-management/billing-account.md)
- [Recharge](https://docs.scitix.ai/account/account-management/recharge.md)
- [Vouchers](https://docs.scitix.ai/account/account-management/vouchers.md)
- [Orders](https://docs.scitix.ai/account/billing/orders.md)
- [Bills](https://docs.scitix.ai/account/billing/bills.md)
- [Bill Details](https://docs.scitix.ai/account/billing/bill-details.md)
- [Billing Method](https://docs.scitix.ai/account/billing/billing-method.md)
- [How to Get Access Keys (AK/SK)](https://docs.scitix.ai/account/faq/get-ak-sk.md)
- [Model Launch Records](https://docs.scitix.ai/changelog/model-launch-records.md): View launch dates, model IDs, and use cases for newly available Model Inference models.
- [Model Inference Release Notes](https://docs.scitix.ai/changelog/model-product-changelog.md): View Model Inference release notes for console, API, observability, usage and billing, stability, and compatibility updates.
- [Console Changelog](https://docs.scitix.ai/changelog/console-changelog.md): Console change history.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.