@ai-sdk/replicate
3.0.85 · 17 Nov 2026Apache-2.0111.4k / weekRepositoryHomepagenpmAtom feed
Upgrading @ai-sdk/replicate From 2.0.67 to 3.0.85
88 releases in betweenevery note read
Reading releases, release notes and advisories…
- 4
- changes to make
- 0
- advisories fixed
- 5
- new
- 14
- fixes
Before you upgrade
Tick each one off as you go- Breaking3.0.0
- Breaking3.0.0
- Breaking3.0.0
- Breaking3.0.0
Release by release
3.0.85nothing new or fixed in the note
- Fixed
Derive known model ID suggestions from each provider's model catalog declarations so catalog updates automatically update autocomplete, while preserving existing suggestions, endpoint-specific model lists, and support for custom model IDs.
- Fixed
3.0.78 – 3.0.835 releases, nothing new or fixed in the notes
- Fixed
Refactor Replicate model ID logic into a model catalog that declares capabilities and provider options, and generate provider capability documentation from it. Request behavior is unchanged.
- Fixed
replicate: Cancel abandoned image predictions on abort or poll timeout
- Fixed
- Fixed
Pass through
seed: 0instead of dropping it in image and video models. KlingAI now reportsseed: 0as an unsupported setting like any other seed.
- Fixed
3.0.74 – 3.0.752 releases, nothing new or fixed in the notes
- New
Support promises and synchronous or asynchronous callbacks in provider API key and token settings. Resolve credentials per authenticated request while preserving existing authentication behavior and synchronous credential serialization.
- New
3.0.67 – 3.0.726 releases, nothing new or fixed in the notes
88 internal lines (docs, tests, tooling) left out.
A whole project to check? Paste its package.json in the dependency check: every deprecated, outdated or vulnerable dependency, with what to upgrade to. Free, no account.