Skip to content

Remove deprecated Cerebras llama-3.3-70b from the API reference (VAPICS-1120) - #1196

Open
chiranjeet-vapi wants to merge 1 commit into
VapiAI:mainfrom
chiranjeet-vapi:docs/vapics-1120-remove-deprecated-cerebras-llama-3-3-70b
Open

Remove deprecated Cerebras llama-3.3-70b from the API reference (VAPICS-1120)#1196
chiranjeet-vapi wants to merge 1 commit into
VapiAI:mainfrom
chiranjeet-vapi:docs/vapics-1120-remove-deprecated-cerebras-llama-3-3-70b

Conversation

@chiranjeet-vapi

Copy link
Copy Markdown

Description

  • llama-3.3-70b still appears in the API reference under CerebrasModel.model (Create Assistant) but is deprecated and no longer offered in the Dashboard, so the reference advertises a model customers cannot select. Tracked in VAPICS-1120.
  • fern/apis/api/openapi.json is re-synced from the live spec daily, so the change is made in fern/apis/api/openapi-overrides.yml instead: the existing CerebrasModel override gains a model entry that restricts the enum to llama3.1-8b and adds a description noting the deprecation. This keeps the rendered API reference consistent with providers/model/cerebras, which already lists only llama3.1-8b.
  • Docs-only. The backend enum still accepts llama-3.3-70b; removing it there is a separate change in the API repo. fern check passes (0 errors; the 12 warnings are pre-existing tool discriminator-mapping warnings on main).

Testing Steps

  • Run the app locally using fern docs dev or navigate to preview deployment
  • Ensure that the changed pages and code snippets work (Create Assistant and Update Assistant, model > Cerebras should list only llama3.1-8b)

🤖 Generated with Claude Code

…CS-1120)

The synced openapi.json still lists llama-3.3-70b under CerebrasModel.model,
but the model is deprecated and no longer offered in the Dashboard, so the
API reference advertised a model customers cannot select. Since openapi.json
is regenerated daily, the change lives in openapi-overrides.yml: the existing
CerebrasModel override now restricts model.enum to llama3.1-8b and notes the
deprecation. providers/model/cerebras already lists only llama3.1-8b, so the
reference and the provider page now agree. Docs-only; the backend enum is a
separate change.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
@lightsage-app

lightsage-app Bot commented Sep 6, 2026

Copy link
Copy Markdown

Lightsage docs evals

Waiting for the staging docs URL before running evals.

Lightsage will start the selected PR evals automatically when GitHub reports a successful docs deployment for this PR. This usually happens within 15 minutes.

Commit: 0129367
Status: waiting for staging docs URL

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant