> ## Documentation Index
> Fetch the complete documentation index at: https://www.edgee.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Codex Compression
> The three Edgee compression strategies, tuned for Codex. Each strategy is independently toggleable.
**Codex Compression** is the Edgee compression bundle tuned for Codex traffic — the three named strategies described in [Token Compression](/features/token-compression), pre-configured for the OpenAI Responses wire format that Codex uses.
You choose which strategies to enable. The CLI turns on a sensible default; the Console lets you toggle each one per API key.
| Strategy | What it does for Codex | Default | Customer-traffic average |
| ------------------------ | ----------------------------------------------------------------------------------------------------------- | --------- | ------------------------ |
| **Tool Result** | Trims tool-call outputs (file reads, shell commands, search results) before they reach the model. Lossless. | ✅ on | **−19%** |
| **Tool Surface** (alpha) | Drops MCP servers, skills, and tools irrelevant to the current task before the request hits the model. | ⚠️ opt-in | **\~−25%** projected |
| **Output** | Reduces verbosity of model responses without losing technical content. Same answer, fewer tokens. | ⚪ opt-in | **−6.5%** when enabled |
Per-strategy averages don't aggregate — they're measured on different baselines. Customer aggregate token-bill reduction across active customers (rolling 30 days) sits at approximately **20%**, with zero measurable drift on SWE-Bench Verified samples.
## Tool Result Trimming
`tool_result_trimming` filters the tool-call outputs Codex receives — file reads, shell commands, search results — before they reach the model. Lossless on tool-result payloads. User messages and assistant turns are not modified.
→ Full strategy reference: [Token Compression / Tool Result Trimming](/features/token-compression#tool-result-trimming).
## Tool Surface Reduction (alpha)
`tool_surface_reduction` strips out the MCP servers, skills, and tools Codex wouldn't use for the current task. The IDE still exposes everything; the model only ever sees the relevant subset.
→ Full strategy reference: [Token Compression / Tool Surface Reduction](/features/token-compression#tool-surface-reduction).
## Output Brevity (by Caveman)
`output_brevity` reduces the verbosity of Codex's responses. Three strategies are available (`light`, `medium`, `hard`). Off by default for Codex sessions because output is a small share (\~1%) of total volume — turn it on if your Codex workflow leans heavy on long-form responses.
→ Full strategy reference: [Token Compression / Output Brevity](/features/token-compression#output-brevity-by-caveman).
## Receipts
> **−49.5%** fresh input tokens (1.14M → 574K per session). **−35.6%** total session cost ($4.00 → $2.58). Cache hit rate **76% → 85%**.
>
> Source: [`edgee-ai/compression-lab`](https://github.com/edgee-ai/compression-lab) · [Stop paying Codex to re-read context](https://www.edgee.ai/blog/posts/stop-paying-codex-to-re-read-context)
## Get started
```bash theme={"dark"}
edgee launch codex
```
If the Edgee CLI isn't installed yet:
```bash theme={"dark"}
curl -fsSL https://install.edgee.ai | bash
```
```bash theme={"dark"}
brew install edgee-ai/tap/edgee
```
```powershell theme={"dark"}
irm https://install.edgee.ai/install.ps1 | iex
```
After your session, the CLI prints a link to view per-strategy savings in the Edgee Console.
Install, authenticate, and launch Codex in under a minute.
## Codex-specific: OpenAI Responses wire format
Codex uses the OpenAI `responses` wire API. When routing through Edgee, the CLI automatically sets the correct provider config in `~/.codex/config.toml`:
```toml theme={"dark"}
model_provider = "edgee"
[model_providers.edgee]
name = "EDGEE"
base_url = "https://api.edgee.ai/v1"
http_headers = { "x-edgee-api-key" = "" }
wire_api = "responses"
```
This is handled automatically by `edgee launch codex`. You never need to edit this file manually.
## Toggling individual strategies
In the [Edgee Console](https://www.edgee.ai), open **Dashboard** and manage your Codex's settings right from the UI.
* Enable `tool_surface_reduction` to opt into the alpha tool-surface compression.
* Enable `output_brevity` if your Codex workflow produces long-form output worth tightening.
* Disable `tool_result_trimming` only when you want to compare against an uncompressed baseline.
For team-managed keys, the same toggles are available per-member from **Team management → agent settings**. See [Team management](/features/team).
To configure Codex without the CLI, paste the config above into `~/.codex/config.toml` and replace `` with your key from the [Edgee Console](https://www.edgee.ai). Then enable the strategies you want from the **Edge Models** section.
## Lossiness
`tool_result_trimming` is lossless on tool-result payloads. `tool_surface_reduction` is lossless on the model's perspective of available tools. `output_brevity` is **not** lossless on the prose dimension — it intentionally compresses prose verbosity. Across active customers (rolling 30 days), aggregate token bills are reduced by approximately **20%** with zero measurable drift on SWE-Bench Verified samples.
## Next
Deep dive on each strategy.
Same three strategies, tuned for Claude Code.