Portkey-AI/gateway
120 source files scanned · 5 LLM call site(s) · ~0% of LLM spend looks recoverable (static heuristics · repo looks like an app)
$80per 10k runs today (gpt-4o, ~2000 prompt tokens)
$80per 10k runs with fixes applied
[](https://tokenzero.sh/audit/portkey-ai/gateway)
Models referenced
gpt-3.5-turbo ×4gpt-4o ×1 (cheaper sibling: gpt-4o-mini)
Findings
| Severity | Where | Finding | Est. |
|---|---|---|---|
| low | cookbook/integrations/vercel/app/examples/generate-ui-streamui/action.tsx:51 | "gpt-4o" retires on 2027-01-14 The provider announced on 2026-10-14 that this model retires on 2027-01-14 (80 days). Recommended replacement: gpt-6-luna. Fix: Move to gpt-6-luna (eval first); TokenZero's cascade can route to it, and the gateway warns in X-TokenZero-Warning until you do. | 0% |
| info | cookbook/integrations/vercel/app/examples/generate-text/conditional-routing.ts:50 | Unrecognised model id "gpt-3.5-turbo" Not in the current pricing table: it may be retired or renamed. Retired models return errors or are silently remapped by some providers. Fix: Check the provider model list; TokenZero flags unpriced models in `X-TokenZero-Warning`. | 0% |
Fix all of it with one line
OPENAI_BASE_URL=https://tokenzero.sh/v1 ANTHROPIC_BASE_URL=https://tokenzero.sh
Keys pass through untouched. Cache formatting and exact caching are on by default; cascade routing stays opt-in. How it works