Documentation

id: getting-started group: Setup title: Getting Started summary: Get up and running with a hosted chat or the OpenAI-compatible API in a few minutes. keywords:

• quickstart
• signup
• api key
• onboarding featured: true quickLinkDescription: Launch chat + send your first completion. search:
• Step-by-step onboarding: sign up, chat, create an API key, and send your first completion.
• Includes cURL, Node.js, and Python examples for calling the chat completions endpoint.

Getting Started

Get up and running with LLM Portal in a few simple steps. Use the hosted chat or integrate via REST.

id: migration group: Setup title: Migration summary: Drop-in compatible with OpenAI and Anthropic clients — swap only the base URL, model ID, and auth header. keywords:

• openai
• anthropic
• compatibility
• base_url search:
• Explains the minimal changes required when moving from OpenAI or Anthropic endpoints.
• Comparison tables cover base URLs, auth headers, endpoints, and model identifiers.

Migration

LLM Portal provides an OpenAI-compatible API. If you are migrating from OpenAI or Anthropic Claude, the transition requires minimal changes.

From OpenAI

The API is fully compatible with the OpenAI format. You only need to change three things:

Everything else — request/response format, streaming, function calling, message roles — works identically. You can use the OpenAI Python or Node.js SDK by simply overriding the base_url.

From Claude (Anthropic)

LLM Portal natively supports the Anthropic Claude API format. The API auto-detects the format and responds accordingly. Your existing Claude request bodies — including the top-level system field, input_schema tool definitions, tool_use/tool_result content blocks, and Anthropic-style responses — work without any conversion. You only need to change:

See the Migrate from OpenAI and Migrate from Claude step-by-step guides for detailed examples and code samples.

id: authentication group: Setup title: Authentication summary: API keys, cookie-based sessions, OAuth, and TOTP-based two-factor authentication. keywords:

• oauth
• '2fa'
• sso
• session search:
• Details API key bearer auth plus session cookies managed by NextAuth.
• Covers OAuth providers, TOTP setup commands, and password requirements.

Authentication

LLM Portal supports multiple authentication methods depending on your use case.

API Key Authentication

For programmatic access, include your API key in the Authorization header as a Bearer token. API keys can be scoped with specific permissions and rate limits.

Session Authentication

Browser-based access uses secure HTTP-only cookies managed by NextAuth. Sessions are created automatically when you sign in through the web interface. Session tokens are JWT-based and refresh automatically.

OAuth Providers

Sign in with your existing Google or GitHub account. OAuth accounts are automatically linked if the email address matches an existing account.

Two-Factor Authentication (2FA)

Enhance your account security by enabling TOTP-based two-factor authentication. Once enabled, you will need to provide a 6-digit code from your authenticator app (e.g., Google Authenticator, Authy) each time you sign in. Backup codes are provided during setup for account recovery.

Password Requirements

Passwords must be at least 12 characters and include uppercase letters, lowercase letters, numbers, and special characters. Password changes require your current password for verification.

id: chat-interface group: Features title: Chat Interface summary: "Explore the hosted chat features: streaming responses, code highlighting, attachments, ratings, and voice input." keywords:

• ui
• messages
• streaming
• attachments featured: true quickLinkDescription: Real-time streaming, uploads, ratings. search:
• Describes conversations, streaming tokens, syntax highlighting, and attachments.
• Mentions rating controls and microphone-based voice input.

Chat Interface

The web-based chat interface provides a rich conversational experience with real-time streaming, code highlighting, file attachments, and more.

Conversations

Messages are organized into sessions (conversations). Each session maintains its own context and message history. You can create new sessions, rename them, and switch between them from the sidebar. Sessions are automatically titled based on the first message.

Streaming Responses

Responses stream in real-time using Server-Sent Events (SSE). You see each token as it is generated, providing immediate feedback. Streaming can be used both in the web interface and via the API by setting stream: true.

Code Highlighting

Code blocks in AI responses are automatically syntax-highlighted with a VS Code-inspired theme. Supported languages include JavaScript, TypeScript, Python, Java, Go, Rust, SQL, HTML, CSS, and many more. Each code block includes a copy button and line numbers.

File Attachments

Attach files to your messages for the AI to analyze. Supported file types include images (PNG, JPG, GIF, WebP), PDFs, documents, spreadsheets, and code files. Each file can be up to 50MB, with a maximum of 5 files per message.

Message Ratings

Rate AI responses with thumbs up or thumbs down to help improve response quality. Ratings are tracked and can be used for analytics.

Voice Input

Use the microphone button to dictate messages using speech-to-text. Voice input uses a WebSocket connection for real-time transcription.

id: api-keys group: Features title: API Keys summary: Manage scoped API credentials with permissions, rate limits, and IP whitelists. keywords:

• keys
• scopes
• rate limits
• rotation featured: true quickLinkDescription: Create scoped keys and rotate safely. search:
• Shows JSON payload for creating keys with permissions and limits.
• Explains permissions matrix, RPM limits, IP whitelisting, and lifecycle states.

API Keys

API keys provide programmatic access to the LLM Portal API. Each key can be configured with specific permissions, rate limits, and IP restrictions.

Creating Keys

Create API keys from the web dashboard or via the API. The number of keys you can create depends on your subscription plan (1 for Free, 10 for Pro, unlimited for Enterprise). The full key value is shown only once at creation — store it securely.

Permissions

API keys support granular permissions to restrict what operations the key can perform:

Rate Limits

Each key can have configurable rate limits: requests per minute (RPM), daily token limit, and monthly token limit. When a limit is exceeded, the API returns a 429 Too Many Requests response.

IP Whitelisting

Restrict API key usage to specific IP addresses or CIDR ranges. Requests from non-whitelisted IPs will be rejected with a 403 Forbidden response.

Key Lifecycle

API keys can be in one of three states: Active, Revoked, or Expired. You can regenerate a key to get a new secret while keeping the same configuration. Revoked keys can be reactivated if needed. Keys can also be set to auto-expire after a specified number of days.

id: models group: Features title: Models summary: List available model IDs and tune sampling parameters for completions. keywords:

• models
• temperature
• sampling featured: true quickLinkDescription: Available IDs and sampling parameters. search:
• Includes cURL example for listing models and JSON response sample.
• Table documents parameters like temperature, messages, stream flag, and session_id.

Models

LLM Portal provides access to AI models for text generation, analysis, and conversation.

Available Models

Query the models endpoint to see all available models. Each model has an ID and provider.

Model Parameters

When sending a chat completion request, you can configure the following parameters:

id: function-calling group: Features title: Function Calling summary: Define tools the model can invoke, with both OpenAI- and Anthropic-style payloads. keywords:

• tools
• functions
• tool_choice search:
• Explains tool definition differences between OpenAI and Anthropic formats.
• Covers tool_choice options, parallel tool calls, and multi-turn workflow.

Function Calling

Extend the model's capabilities by defining custom functions (tools) that it can invoke during a conversation. The API supports both OpenAI and Anthropic tool formats natively — the format is auto-detected based on your request structure.

How It Works

You define tools in your API request. When the model determines a tool should be used, it returns the function name and structured arguments. You execute the function on your side, then send the result back in a follow-up request. The model then generates a final response using the tool output.

Supported Formats

The API auto-detects which format you are using and responds in the same style:

Tool Definitions

Controlling Tool Use

Parallel Tool Calls

The model can call multiple tools in a single response. For example, asking "What's the weather in Athens and London?" may produce two tool calls in the same response. Each has a unique ID — submit results for all of them before making the next completion request.

Multi-Turn Flow

The complete function calling flow involves three steps:

1. Send a request with tools defined. The model returns tool calls with function names and arguments.
2. Execute the function(s) on your side using the arguments provided by the model.
3. Send the results back (as tool role messages in OpenAI format, or tool_result content blocks in Anthropic format). The model generates a natural language response.

See the API Reference for complete request/response examples, and the Function Calling Guide for a step-by-step tutorial.

id: usage-analytics group: Account title: Usage & Analytics summary: Track token consumption, latency, and trends via dashboards or the usage API. keywords:

• metrics
• charts
• dashboard search:
• Describes dashboard charts plus usage API filters by model and key.
• Lists metrics such as tokens, cost, latency, and shows per-key usage endpoint.

Usage & Analytics

Monitor your API consumption, track costs, and analyze usage patterns through the usage dashboard or API endpoints.

Usage Dashboard

The web dashboard provides visual charts showing your request volume, token consumption, cost breakdown, and error rates over time. Filter by date range, API key, model, and request status.

Querying Usage via API

Use the usage API to programmatically retrieve your consumption data. Supports filtering by time period, API key, and model.

Metrics Tracked

Alerts

Set up usage alerts to receive notifications when you approach or exceed token or cost thresholds. Alerts can be sent via email or Slack.

Per-Key Usage

View usage statistics for individual API keys, including daily breakdowns and request history:

id: billing group: Account title: Billing & Plans summary: Compare plans, manage payment methods, and retrieve invoices via the API. keywords:

• pricing
• plans
• invoice search:
• Plan comparison table plus Stripe-based payment method guidance.
• API endpoints for listing invoices and previewing plan changes, plus cancellation policy.

Billing & Plans

LLM Portal offers flexible subscription plans to match your usage needs. Billing is securely handled through Stripe.

Subscription Plans

Choose between Free, Pro, and Enterprise plans. Each plan includes a different allocation of monthly tokens, API keys, and features. Plans can be changed at any time with prorated billing.

Payment Methods

Add credit or debit cards as payment methods through the billing dashboard. You can have multiple cards on file and set a default for recurring charges. All payment processing is handled securely by Stripe — card details never touch our servers.

Invoices

View and download invoices for all past payments. Invoices include a breakdown of token usage, plan charges, and any prorated adjustments from plan changes.

Cancellation

You can cancel your subscription at any time. Cancellation takes effect at the end of your current billing period — you retain access to Pro features until then. If you exceed the included tokens for your plan, overage is billed at the end of the billing cycle. Configure alerts to be notified before you reach your token allotment.

id: content-library group: Content title: Content Library summary: Archive assets from conversations—images, files, code, and notes—with tags and search. keywords:

• files
• canvas
• library search:
• Outlines content types (images, video, documents, code, notes) and tagging.
• Shows search and stats API calls for filtering favorites and checking storage usage.

Content Library

Save and organize content from your AI conversations into a personal library. Content items include images, videos, files, code snippets, conversations, and notes.

Content Types

Organizing Content

Use tags, favorites, and collections to keep your library organized. Content items support full-text search across titles, descriptions, and tags. Filter by type, source, favorite status, and archive status.

Storage

Each account has a storage limit based on your subscription plan. Track your storage usage through the content statistics endpoint. File uploads are limited to 50MB per file.

id: collections group: Content title: Collections summary: Group related content items with custom names, colors, and icons. keywords:

• organization
• tags
• folders search:
• Covers creation payload for collections and managing membership via REST calls.
• Mentions sharing options with role-based permissions.

Collections

Group related content items into collections for better organization. Each collection can have a custom name, description, color, and icon.

Creating Collections

Create collections from the content library page or via the API. A default collection is created automatically for each new account.

Managing Items

Add or remove content items from collections. An item can belong to multiple collections. Default collections cannot be deleted.

Sharing

Collections can be shared with teammates on Enterprise plans. Shared collections support role-based permissions (viewer, editor, owner) and activity history.

id: canvas group: Content title: Canvas Documents summary: Pair each chat session with a collaborative Canvas document that supports version history. keywords:

• canvas
• documents
• editor search:
• Explains real-time collaboration, presence, and version snapshot limits.
• Provides API requests for fetching, updating, and snapshotting canvas documents.

Canvas Documents

Canvas is a collaborative document editor linked to chat sessions. Use it to draft, edit, and iterate on content alongside your AI conversations.

How Canvas Works

Each chat session can have an associated canvas document. The canvas stores content alongside the conversation, allowing you to work on a document while discussing it with the AI. Canvas documents support version history with up to 50 snapshots.

Live Collaboration

Multiple collaborators can edit the same canvas in real time. Presence indicators show who is currently editing, along with their cursor position. Changes are synced instantly through our WebSocket infrastructure.

Version History

Canvas automatically tracks changes through version snapshots. You can view, compare, and restore previous versions. When the maximum of 50 versions is reached, the oldest versions are automatically removed.

id: files group: Content title: Files & Uploads summary: Supported file types, upload limits, and multipart endpoints for attaching assets. keywords:

• uploads
• multipart
• storage search:
• Lists supported formats across images, documents, data, code, and video.
• Shows multipart cURL examples for uploading to chat and the content library.

Files & Uploads

Upload files for AI processing or attach them to chat messages. The platform supports a wide range of file types.

Supported File Types

Upload Limits

Maximum file size is 50MB per file. Chat attachments are limited to 5 files per message. Files are processed through the LLM backend for AI analysis.

id: security group: Security title: Security summary: Transport encryption, strict headers, rate limiting, and account-hardening defaults. keywords:

• tls
• hsts
• headers featured: true quickLinkDescription: Transport encryption and headers overview. search:
• Details TLS/HSTS posture, custom headers, and session hardening guidance.
• Covers account security best practices and rate limiting rules.

Security

LLM Portal is built with security as a priority. Here is an overview of the security measures in place.

Transport Security

All traffic is encrypted with TLS (HTTPS). HTTP Strict Transport Security (HSTS) is enforced with a max-age of 2 years and includeSubDomains. API keys and session tokens are only transmitted over encrypted connections.

Security Headers

The platform sets comprehensive security headers on all responses:

Account Security

Protect your account with strong passwords (minimum 12 characters), two-factor authentication, and API key IP whitelisting. Session tokens use secure, HTTP-only cookies that are not accessible to JavaScript.

Rate Limiting

Authentication endpoints are rate-limited to prevent brute-force attacks. API keys support configurable per-minute, daily, and monthly rate limits. Excessive requests return a 429 status code with a Retry-After header.