Cursor: semantic caching in one line
Byte-identical repeats are served from the exact cache at $0 and near-duplicates from the opt-in semantic cache. 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. Every byte-identical repeat is served at $0: at a 20% repeat share, 100,000 reference calls on gpt-6.1-sol cost $560 instead of $700 a month; the semantic cache extends that to near-duplicates when you opt in.
· Source: pricing table 2026-10-26; overhead from the published benchmark on /benchmarks
At a glance
- Framework
- Cursor (Settings)
- Capability
- semantic caching
- Change
- Cursor Settings → Models: environment / settings
- Request shape
- any official SDK via environment
- Turn it on
- X-TokenZero-Semantic-Cache: true
- Workspace setting
- semantic_cache: true, cache_ttl: 3600
- Reference model
- gpt-6.1-sol ($2.00 in / $10.00 out per 1M, table 2026-10-26)
- Exact-cache saving at a 20% repeat share
- $140/month (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 semantic caching. Per request: X-TokenZero-Semantic-Cache: true (exact cache is automatic for temperature-0 or seeded requests; X-TokenZero-Cache: always forces it). Per workspace (applies to every call without touching code): PATCH /v1/workspaces/settings {semantic_cache: true, cache_ttl: 3600} 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 cache_hit_rate_pct and savings from engine cache 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 semantic caching save on gpt-6.1-sol?
Every byte-identical repeat is served at $0: at a 20% repeat share, 100,000 reference calls on gpt-6.1-sol cost $560 instead of $700 a month; the semantic cache extends that to near-duplicates when you opt in.
Does semantic caching change the model's output?
The exact cache returns the provider's own earlier response for a byte-identical request; the semantic cache is opt-in and only matches within the distance you accept. Non-deterministic requests are never cached unless you force it.
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.