OpenAI Codex CLI: 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 OpenAI Codex CLI, the switch that turns it on, and the arithmetic on gpt-6.1-sol.
OpenAI Codex CLI reaches TokenZero with one environment or settings change 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
- OpenAI Codex CLI (Shell)
- Capability
- prompt compression
- Change
- ~/.codex/config.toml: environment / settings
- Request shape
- any official SDK via environment
- 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 OpenAI Codex CLI at the gateway (~/.codex/config.toml):
+export OPENAI_BASE_URL=https://tokenzero.sh/v1 +# ~/.codex/config.toml +[mcp_servers.tokenzero] +command = "npx" +args = ["-y", "@tokenzero/mcp"] codex
Codex honours OPENAI_BASE_URL and reads AGENTS.md, which npx -y @tokenzero/cli init --agent-rules fills in.
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 OpenAI Codex CLI at TokenZero?
Set the base URL where OpenAI Codex CLI configures its provider (~/.codex/config.toml) to https://tokenzero.sh/v1 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.