vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-04-12 01:31:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs(openai): clarify gpt-5.4 fast mode

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-06 01:20:40 +01:00
parent 699b2320a8
commit 9b00008561
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/providers/openai.md
View File

@@ -401,6 +401,12 @@ When fast mode is enabled, OpenClaw maps it to OpenAI priority processing:
- existing payload `service_tier` values are preserved
- fast mode does not rewrite `reasoning` or `text.verbosity`
For GPT 5.4 specifically, the most common setup is:
- send `/fast on` in a session using `openai/gpt-5.4` or `openai-codex/gpt-5.4`
- or set `agents.defaults.models["openai/gpt-5.4"].params.fastMode = true`
- if you also use Codex OAuth, set `agents.defaults.models["openai-codex/gpt-5.4"].params.fastMode = true` too
Example:
```json5