Next.js + Vercel AI SDK: prompt compression in one line
The static prefix is formatted for the provider cache (Anthropic breakpoints, OpenAI prompt_cache_key or 12h retention) and tool schemas are minified losslessly before they are sent. Here is the change for Next.js + Vercel AI SDK, the switch that turns it on, and the arithmetic on gpt-6.1-sol.
Next.js + Vercel AI SDK reaches TokenZero with one base-URL argument and keeps your openai key. On gpt-6.1-sol a cached input token costs $0.100 per million instead of $2.00, so 100,000 calls with a 1,500-token static prefix drop from $700 to $415 a month, 41% less, before any routing.
· Source: pricing table 2026-10-26; overhead from the published benchmark on /benchmarks
At a glance
- Framework
- Next.js + Vercel AI SDK (TypeScript)
- Capability
- prompt compression
- Change
- app/api/chat/route.ts: base URL argument
- Request shape
- OpenAI chat / Responses
- Turn it on
- X-TokenZero-Cache-Strategy: static
- Workspace setting
- cache_strategy: static, prompt_cache_ttl: 1h
- Reference model
- gpt-6.1-sol ($2.00 in / $10.00 out per 1M, table 2026-10-26)
- Cache-formatting saving on the reference workload
- $285/month (41%) (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 Next.js + Vercel AI SDK at the gateway (app/api/chat/route.ts):
-import { openai } from '@ai-sdk/openai';
+import { createOpenAI } from '@ai-sdk/openai';
+const openai = createOpenAI({ baseURL: 'https://tokenzero.sh/v1', apiKey: process.env.OPENAI_API_KEY });
const result = streamText({ model: openai('gpt-6.1-sol'), messages });streamText and generateText keep working; streaming responses end with a signed receipt trailer.
2. Turn on prompt compression. Per request: X-TokenZero-Cache-Strategy: static (default) · X-TokenZero-Prompt-Cache-TTL: 1h or 12h. Per workspace (applies to every call without touching code): PATCH /v1/workspaces/settings {cache_strategy: static, prompt_cache_ttl: 1h} 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 input_tokens_cached_pct and compaction tokens saved on the scorecard.
Questions people ask
How do I point Next.js + Vercel AI SDK at TokenZero?
Pass base_url / baseURL = https://tokenzero.sh/v1 where Next.js + Vercel AI SDK builds its client (app/api/chat/route.ts) and keep your openai key; nothing else changes.
What does prompt compression save on gpt-6.1-sol?
On gpt-6.1-sol a cached input token costs $0.100 per million instead of $2.00, so 100,000 calls with a 1,500-token static prefix drop from $700 to $415 a month, 41% less, before any routing.
Does prompt compression change the model's output?
No. Cache formatting only marks or keys the static prefix and tool minification only collapses whitespace in descriptions; names, enums, defaults and examples are never touched.
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.