Use period · switch tiers / missing from the list

Run GPT-5.6 in Codex CLI

The live question is not “did 5.6 ship” — it is how to switch tiers in Codex and what to do when Sol is missing from /model. ChatGPT-signed-in Codex loses GPT-5.4 starting 2026-08-31 (rechecked 2026-08-30, still “starting August 31”); API-key profiles pick gpt-5.6-sol / terra / luna with /model; QCode profiles pick gpt-5.6-sol / terra, as QCode does not currently support Luna — please use another GPT model.

#GPT-5.6 #gpt-5.6-sol #Codex CLI #QCode

Why doesn't /model show gpt-5.6?

Two model lists get mixed up: ChatGPT-signed-in Codex is not the same list as an API-key / QCode profile. Older CLI builds also omit the three gpt-5.6-* tiers from /model. Confirm how you authenticate, then update the CLI — do not treat a missing row as a retirement first.

Before you start

Node.js 18+ and npm (to install / update Codex CLI)
A QCode.cc API key (issued when you activate any plan, from $8.57/mo; one key covers Claude / GPT / Gemini)
About 5 minutes

Step 1: Update Codex CLI to the latest version

The GPT-5.6 tiers ship built in from releases around July 2026. One global update command does it; confirm with codex --version afterwards.

Terminal — update Codex CLI

# update to the latest Codex CLI
npm install -g @openai/codex@latest

# confirm the version
codex --version

Step 2: Add a QCode profile to config.toml

Add the QCode provider and profile to ~/.codex/config.toml so requests go to the QCode endpoint with your API key. Full details are in the Codex quick-start in the QCode docs.

~/.codex/config.toml — QCode profile

# ~/.codex/config.toml — add the QCode profile
# full config reference:
# https://docs.qcode.cc/docs/getting-started/codex-quick-start

model = "gpt-5.6-terra"   # default tier; sol / luna also available

# ... keep your QCode provider / auth settings unchanged

Step 3: Pick a tier with /model (or set it in config)

Launch codex and type /model to switch between gpt-5.6-sol / gpt-5.6-terra, or set model in config.toml as your default. QCode does not currently support gpt-5.6-luna or gpt-6-luna (both removed from /models), so please use another GPT model. Rule of thumb: Terra as default, Sol for the hard parts.

Codex session — switching models

$ codex --profile qcode
> /model
    gpt-5.6-sol
  ● gpt-5.6-terra    ← selected
    gpt-5.6-luna
    gpt-5.5

Step 4: Verify it runs and bills correctly

Run a small task to confirm responses, then check your QCode dashboard usage — you should see calls under the gpt-5.6 tier you picked. All tiers share the same quota as GPT-5.5; nothing extra to buy.

Codex session — verify

$ codex "add a unit test for utils/retry.ts"
# response streams from gpt-5.6-terra

# then: qcode.cc dashboard → usage
# calls appear under the gpt-5.6 tier you selected

FAQ

I can't update the CLI (version-pinned). Can I still use GPT-5.6?

Yes. Older versions can register models manually via the model-catalog mechanism — the process is identical to our earlier GPT-5.5 enablement guide, just with gpt-5.6-sol / terra as the model ids in the JSON (QCode does not currently support Luna). Updating the CLI remains the preferred path though: one command replaces all manual steps.

Which tier should I pick?

Terra for daily work (beats GPT-5.5 at about half of Sol's price); Sol for hard jobs like cross-repo refactors; Luna for completions, batch and light CI tasks (QCode does not currently support Luna — use another GPT model such as gpt-5.6-terra). See our Sol vs Terra vs Luna guide for the full comparison. Sol vs Terra vs Luna →

How do billing and quota work?

gpt-5.6-sol and gpt-5.6-terra share one QCode key and one quota with GPT-5.5, Claude and Gemini, billed by usage. As of 2026-08-30, Sol and Terra match OpenAI's API list: Sol $5/$30, Terra $2/$12 per million tokens; QCode does not currently support gpt-5.6-luna or gpt-6-luna (both removed from /models), so please use another GPT model, such as gpt-6.1-sol, gpt-6-sol or gpt-5.6-terra. Live rates are on /models.

Any difference between calling via QCode and OpenAI directly?

The models and API behavior are the same standard interface. The difference is the onramp: QCode adds China-optimized low-latency endpoints, local payment, and one key across Claude / GPT / Gemini — no self-hosted proxy or overseas payment method needed.

Try GPT-5.6 in Codex now

Create a QCode account, activate a plan from $8.57/mo to get your API key, and run gpt-5.6-sol / gpt-5.6-terra in Codex CLI within five minutes (QCode does not currently support Luna).

See plans and pricing Codex quick-start docs

Create a QCode account

Plans from ¥60 / $8.57. One key across Claude, GPT, and Gemini models.

Create account Browse models View pricing