hosman20 puts the platform on the hook for AI bills

Customers stop bringing their own API keys; the fork now pays the model providers and meters usage centrally.

infrastructureintegration

Until now, anyone using this fork had to plug in their own credentials for Anthropic, Google, or OpenAI and pay those providers directly. hosman20 has ripped that whole arrangement out. All model traffic is funneled through a single routing layer (Vercel's AI Gateway, a service that brokers calls across providers behind one key), and the customer-facing screens for managing API keys are gone.

Every request now carries an identifier for the user and their firm, so cost can be sliced per customer. That's the plumbing a subscription business needs: you can't charge a flat monthly fee for AI usage if the customer is the one holding the meter. This change is the prerequisite for the Stripe paywall and trial limits that ship alongside it - the fork is positioning itself as a paid product for Middle East law firms rather than a bring-your-own-keys prototype.

So what Anyone weighing whether to sell a Mike-based product as a subscription rather than a self-serve tool should look at how this fork made the switch.

View this fork on GitHub →

Spotted something wrong? Or know the PR text has fresher detail than the writeup above?

Commits in this thread

1 commit from hosman20/mike-2.0, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date

07a46ceb feat(llm): replace direct provider SDKs with Vercel AI Gateway z 2026-05-13 ↗ GitHub

SHA	Subject	Author	Date
`07a46ceb`	feat(llm): replace direct provider SDKs with Vercel AI Gateway	z	2026-05-13	↗ GitHub
commit body Batch 4 - route all LLM traffic through the Vercel AI Gateway via AI SDK v6. Tokens are now paid by the platform, not the customer. Backend: - New gateway adapter at backend/src/lib/llm/gateway.ts (uses ai@^6.0.182, "provider/model" strings auto-route via the bundled gateway provider). - 12 unit tests in backend/src/lib/llm/__tests__/gateway.test.ts. - Deleted backend/src/lib/llm/{claude,gemini,openai,tools}.ts and backend/src/lib/userApiKeys.ts - the per-provider SDKs and the customer-key vault are gone. - backend/src/lib/llm/index.ts now re-exports from gateway and routes streamChatWithTools / completeText through it. - backend/src/lib/llm/types.ts: added StreamChatAttribution ({ userId?, orgId? }) for gateway cost-slicing; UserApiKeys kept as @deprecated alias so existing call-sites still typecheck. - backend/src/lib/userSettings.ts: drop per-user api_keys lookup. - backend/src/lib/chatTools.ts: runLLMStream now forwards attribution instead of apiKeys and surfaces aggregate usage.totalTokens. - backend/src/routes/{chat,projectChat,tabular}.ts: attribution ({ userId }) replaces apiKeys; legacy queryGemini/title helpers refactored to take userId. - backend/src/routes/user.ts: deleted GET/PUT /user/api-keys. - backend/.env.example: replaced GEMINI_/ANTHROPIC_/OPENAI_API_KEY and USER_API_KEYS_ENCRYPTION_SECRET with AI_GATEWAY_API_KEY. Frontend: - Deleted frontend/src/app/(pages)/account/models/page.tsx - the user-facing API key UI no longer applies. - frontend/src/app/(pages)/account/layout.tsx: removed the "Models & API Keys" tab (Billing tab arrives in batch 6). Intermediate state notes: - frontend mikeApi.ts still exports getApiKeyStatus + saveApiKey against now-404 routes; UserProfileContext still imports them. Both are cleaned up in batches 6/8. - public.user_api_keys table is not dropped here - orphaned but harmless; can be removed in a follow-up migration. Agent ID: a5511de9cafb2355a (vercel:ai-architect).

commit body

Batch 4 - route all LLM traffic through the Vercel AI Gateway via
AI SDK v6. Tokens are now paid by the platform, not the customer.

Backend:
- New gateway adapter at backend/src/lib/llm/gateway.ts (uses
  ai@^6.0.182, "provider/model" strings auto-route via the bundled
  gateway provider).
- 12 unit tests in backend/src/lib/llm/__tests__/gateway.test.ts.
- Deleted backend/src/lib/llm/{claude,gemini,openai,tools}.ts and
  backend/src/lib/userApiKeys.ts - the per-provider SDKs and the
  customer-key vault are gone.
- backend/src/lib/llm/index.ts now re-exports from gateway and routes
  streamChatWithTools / completeText through it.
- backend/src/lib/llm/types.ts: added StreamChatAttribution
  ({ userId?, orgId? }) for gateway cost-slicing; UserApiKeys kept
  as @deprecated alias so existing call-sites still typecheck.
- backend/src/lib/userSettings.ts: drop per-user api_keys lookup.
- backend/src/lib/chatTools.ts: runLLMStream now forwards attribution
  instead of apiKeys and surfaces aggregate usage.totalTokens.
- backend/src/routes/{chat,projectChat,tabular}.ts: attribution
  ({ userId }) replaces apiKeys; legacy queryGemini/title helpers
  refactored to take userId.
- backend/src/routes/user.ts: deleted GET/PUT /user/api-keys.
- backend/.env.example: replaced GEMINI_/ANTHROPIC_/OPENAI_API_KEY
  and USER_API_KEYS_ENCRYPTION_SECRET with AI_GATEWAY_API_KEY.

Frontend:
- Deleted frontend/src/app/(pages)/account/models/page.tsx - the
  user-facing API key UI no longer applies.
- frontend/src/app/(pages)/account/layout.tsx: removed the
  "Models & API Keys" tab (Billing tab arrives in batch 6).

Intermediate state notes:
- frontend mikeApi.ts still exports getApiKeyStatus + saveApiKey
  against now-404 routes; UserProfileContext still imports them.
  Both are cleaned up in batches 6/8.
- public.user_api_keys table is not dropped here - orphaned but
  harmless; can be removed in a follow-up migration.

Agent ID: a5511de9cafb2355a (vercel:ai-architect).

Capture this thread into my fork

Download a single Markdown prompt that tells Claude how to port every commit above into your working tree — adapting paths and structure to match your repo. Run it via claude -p < capture-thread-406.md from inside the repo you want the changes in.

⬇ Download capture-thread-406.md