Cursor: cascade routing in one line
Prompts the deterministic classifier scores as simple are routed to the cheaper sibling of the model you asked for, inside the same provider, with a shadow-parity breaker. Here is the change for Cursor, the switch that turns it on, and the arithmetic on gpt-6.1-sol.
Cursor reaches TokenZero with one environment or settings change and keeps your openai key. The cascade sibling of gpt-6.1-sol is gpt-6-luna at $0.00035 per reference call against $0.00700; if every call were simple that is $665 a month on 100,000 calls, and a 99.8% parity floor with shadow evaluation decides whether a pair stays enabled.
· Source: pricing table 2026-10-26; overhead from the published benchmark on /benchmarks
At a glance
- Framework
- Cursor (Settings)
- Capability
- cascade routing
- Change
- Cursor Settings → Models: environment / settings
- Request shape
- any official SDK via environment
- Turn it on
- X-TokenZero-Cascade: auto
- Workspace setting
- cascade: auto, shadowEval: true
- Reference model
- gpt-6.1-sol ($2.00 in / $10.00 out per 1M, table 2026-10-26)
- Cascade saving if every simple call moves
- $665/month to gpt-6-luna (computed)
- Gateway overhead (measured)
- 1.52 ms p50, 3.42 ms p95
- Parity floor
- 99.8%
- Free tier
- $500/month routed spend
Reference workload on gpt-6.1-sol: 2,000 input (1,500 static) / 300 output tokens, 100,000 calls per month, table 2026-10-26
| Scenario | Per call | Per month | Delta |
|---|---|---|---|
| List price, no gateway | $0.00700 | $700 | — |
| Static prefix cached (prompt compression) | $0.00415 | $415 | $285 (41%) |
| 20% exact-cache repeats | $0.00560 | $560 | $140 (20%) |
| All calls cascaded to gpt-6-luna | $0.00035 | $35 | $665 (95%) |
| Budget guardrail at $500/month | — | capped at $500.00 | 402 after 71,428 calls |
The change
1. Point Cursor at the gateway (Cursor Settings → Models):
Cursor Settings → Models → OpenAI API Key → "Override OpenAI Base URL" -https://api.openai.com/v1 +https://tokenzero.sh/v1 # plus MCP: npx -y @tokenzero/cli init --mcp (writes .cursor/mcp.json)
The override applies to the models you run with your own key, so the gateway replaces hand-switching between the fast, mid and frontier tiers: simple turns cascade to the cheaper sibling under the parity floor, and the MCP tool schemas Cursor sends are compacted losslessly without breaking the prefix cache.
2. Turn on cascade routing. Per request: X-TokenZero-Cascade: auto (default advise: the recommendation is returned in X-TokenZero-Cascade-Recommendation and nothing moves). Per workspace (applies to every call without touching code): PATCH /v1/workspaces/settings {cascade: auto, shadowEval: true} or the dashboard toggle.
3. Prove it. npx -y @tokenzero/cli doctor checks the gateway, the signer, the pricing table and your key; then watch routed share and parity per pair on the scorecard.
Questions people ask
How do I point Cursor at TokenZero?
Set the base URL where Cursor configures its provider (Cursor Settings → Models) to https://tokenzero.sh/v1 and keep your openai key; nothing else changes.
What does cascade routing save on gpt-6.1-sol?
The cascade sibling of gpt-6.1-sol is gpt-6-luna at $0.00035 per reference call against $0.00700; if every call were simple that is $665 a month on 100,000 calls, and a 99.8% parity floor with shadow evaluation decides whether a pair stays enabled.
Does cascade routing change the model's output?
Only when a prompt is scored simple and the pair is above the 99.8% parity floor; shadow evaluation re-runs a sample on the original model, and a pair that drops below the floor is auto-disabled. Everything else goes to the model you asked for.
What does TokenZero cost?
Free up to $500 per month of routed spend; then 15% of verified savings with a 3x-ROI-or-$0 rule, capped plans available. Gateway overhead measured at 1.52 ms p50.