MandAPI vs n8n vs Tokens Forge vs BitFun

Pricing, plans and key features compared side by side. Updated November 2026.

MandAPI
💻 Coding & Dev
Visit MandAPI →
n8n
💻 Coding & Dev
Visit n8n →
BitFun
💻 Coding & Dev
Visit BitFun →
Pricing model
Paid
Freemium
Freemium
Free
Free plan
✕ No
✓ Yes
✓ Yes
✓ Yes
Paid plans from
Variable (BRL/1M tokens)
~$22/month (annual)
Usage-based
Completely free
Who it's for
MandAPI serves Brazilian developers who want one API for multiple AI models without dealing with USD billing or subscription minimums. The gateway strips away provider lock-in by keeping the OpenAI SDK interface while offering BRL pricing and prepaid credits. Its transparency — published per-model token rates and a public model radar — makes it useful for teams that need predictable costs and fast model switching.
n8n is the automation platform of choice for technical teams that need more than drag-and-drop but less than full custom development. Its fair-code model means you can self-host for free or use the cloud version with execution-based pricing. Companies like Huel and Vodafone use n8n to save thousands of hours by integrating AI into real business workflows in a safe, controlled, and traceable way.
<h3>Why People Use It</h3><p>Tokens Forge appeals to developers and founders who need a single, affordable gateway for multiple AI model providers. Instead of managing separate API keys and billing for OpenAI, Anthropic, and Google, users get one dashboard with transparent per-model pricing and OpenAI-compatible endpoints that drop into existing workflows. The built-in AI Stock Researcher adds unique value for users who need company and market analysis alongside their AI infrastructure.</p>
BitFun gives every task its own interface instead of forcing everything through one chat box, so you work with what's on screen rather than re-describing it. Because it's self-hostable, model-agnostic, and open source, builders who want a fast, private, and deeply customizable desktop agent choose it over cloud-only assistants.
Key features
  • OpenAI-compatible API gateway for 44 models across 10 brands
  • Models from OpenAI, Anthropic, Google, DeepSeek, MiniMax, Kimi, Qwen, Z.ai, Xiaomi, MiMo, and Hunyuan
  • Transparent BRL pricing per 1M tokens with published rate tables
  • Prepaid pay-as-you-go billing via Pix no monthly subscription
  • Use existing OpenAI SDKs by swapping the base URL and API key
  • Connect desktop app for Windows bundles Claude Code and Codex CLI
  • Radar public tracker monitors new model SKUs across vendors
  • Up to 96% savings versus official provider API prices
  • Visual + Code Hybrid Build workflows visually on a canvas, then drop into JavaScript or Python anywhere for custom logic; view inputs/outputs inline
  • AI Agent Orchestration Build multi-agent AI systems with full traceability of reasoning steps; connect any AI model (cloud or offline) with MCP support
  • 500+ Integrations Pre-built nodes for Salesforce, ServiceNow, Asana, Zoom, and more; custom API connections for proprietary or legacy systems
  • Self-Hosting Option Deploy on-premises via Docker for full data control; Community Edition is free and open-source with 193,000+ GitHub stars
  • Human-in-the-Loop Governance Enforce structured inputs/outputs, combine human approvals with automated logic, and set guardrails on AI actions
  • Execution-Based Pricing Pay for full workflow executions, not per step; unlimited users and workflows on every plan
  • Debugging & Observability Re-run single steps, replay or mock data, native AI evaluation, audit logs, and log streaming to SIEM
  • Enterprise Security SSO/SAML/LDAP, encrypted secret stores, RBAC permissions, Git version control, and dedicated support with SLA
  • One OpenAI-compatible endpoint for GPT, Claude, and Gemini models
  • Transparent per-model pricing with per-1M-token settlement rates
  • Dashboard for API key management, balance tracking, and usage monitoring
  • Built-in AI Stock Researcher for company and market reports
  • Works with Cursor-style clients, Open WebUI, Dify, LiteLLM, and custom apps
  • Multiple billing credit packages (10, 25, 100 credits) plus free starter credits
  • Backup channels for reliability
  • New users can test the API before committing to a larger balance
  • Agentic Mini Apps each task gets its own interface (chart, board, form, panel) with a conversation bound to that interface's live state
  • Self-hosted multi-device control login, cross-device session sync, and remote device control through a zero-knowledge relay you deploy
  • Coding plan, edit, test, and commit inside real Git repositories with Agentic, Plan, Debug, and Deep Review modes
  • Office work research, writing, presentations, meeting notes, and reports
  • Desktop execution drives the browser, terminal, desktop apps, filesystem, and remote workspaces
  • Four-tier customization Custom Agents, MCP/Skills/Hooks, Mini Apps, and source-level changes
  • Performance 98.67% average KV cache hit rate and flashgrep for Chromium-scale repo search about 36x faster
  • Cross-platform and model-agnostic Windows, macOS, and Linux; you choose what it runs on
All plans
Pay-As-You-Go Variable (BRL/1M tokens)
Prepaid credits only; no monthly fee; prices vary by model
Community Edition Free (self-hosted)
Full source code on GitHub, unlimited workflows and users, 500+ integrations, visual + code building
Starter (Cloud) ~$22/month (annual)
2,500 executions/month, 1 shared project, 5 concurrent executions, 50 AI credits, forum support
Pro (Cloud) ~$55/month (annual)
10,000 executions/month, 3 shared projects, 20 concurrent executions, 150 AI credits, 7-day insights, admin roles
Business (Cloud) ~$730/month (annual)
40,000 executions/month, 6 shared projects, SSO/SAML/LDAP, 30-day insights, Git version control, different environments
Enterprise Custom
Unlimited projects, 200+ concurrent executions, 365-day insights, 1,000 AI credits, external secret store, log streaming, dedicated support with SLA, invoice billing
Free $0
Starter credits available for new users to test the API.
Pay-as-you-go Usage-based
GPT-5.4 from $0.83/$4.95 per 1M tokens (input/output). GPT-5.5 from $5.50/$33. per 1M. Claude and Gemini models also available at varying per-token rates.
Credit Packages One-time purchase
Buy 10, 25, or 100 credits in advance for sustained usage without recurring subscription.
Free $0
Open-source (MIT); bring your own model key for LLM use.
Profile views
89 on OnePlaceForAI
370 on OnePlaceForAI
471 on OnePlaceForAI
340 on OnePlaceForAI
Build a different comparison →
New AI tools, every Monday Free weekly digest — tool picks, prompts, and AI news.