@ai-sdk/black-forest-labs
2.0.86 · 17 Nov 2026Apache-2.029.2k / weekRepositoryHomepagenpmAtom feed
197 stable releases, newest first, by release line. Notes are quoted as the maintainers published them.
- 2.x · latest line
2.0.23 – 2.0.3411 releases that only update dependencies@ai-sdk/provider-utils 5.0.33@ai-sdk/provider 4.0.8Show each
- 2.0.3428 Aug 2026@ai-sdk/provider-utils 5.0.33
- 2.0.3326 Aug 2026@ai-sdk/provider-utils 5.0.32
- 2.0.3125 Aug 2026@ai-sdk/provider 4.0.8@ai-sdk/provider-utils 5.0.30
- 2.0.3022 Aug 2026@ai-sdk/provider-utils 5.0.29
- 2.0.2919 Aug 2026@ai-sdk/provider-utils 5.0.28
- 2.0.2811 Aug 2026@ai-sdk/provider-utils 5.0.27
- 2.0.2710 Aug 2026@ai-sdk/provider-utils 5.0.26
- 2.0.267 Aug 2026@ai-sdk/provider 4.0.7@ai-sdk/provider-utils 5.0.25
- 2.0.257 Aug 2026@ai-sdk/provider-utils 5.0.24
- 2.0.246 Aug 2026@ai-sdk/provider 4.0.6@ai-sdk/provider-utils 5.0.23
- 2.0.236 Aug 2026@ai-sdk/provider-utils 5.0.22
2.0.22
5 Aug 2026Report the settled cost for FLUX 3 video generations. The submit response can only estimate, and returns no cost when the price depends on the finished video; the result endpoint answers with
SettledCostResultResponse, whose cost was being dropped.
2.0.21
4 Aug 2026Add video model support to the Black Forest Labs provider (
blackForestLabs.video) for the FLUX 3 video model, including text-to-video, image-to-video keyframes, video continuation, draft/draft-enhance generation, and AI SDK Core polling.
Patch Changes
Add video model support to the Black Forest Labs provider (
blackForestLabs.video) for the FLUX 3 video model, including text-to-video, image-to-video keyframes, video continuation, draft/draft-enhance generation, and AI SDK Core polling.
2.0.10 – 2.0.2011 releases that only update dependencies@ai-sdk/provider-utils 5.0.20@ai-sdk/provider 4.0.5Show each
- 2.0.204 Aug 2026@ai-sdk/provider-utils 5.0.20
- 2.0.193 Aug 2026@ai-sdk/provider 4.0.5@ai-sdk/provider-utils 5.0.19
- 2.0.1831 Jul 2026@ai-sdk/provider-utils 5.0.18
- 2.0.1731 Jul 2026@ai-sdk/provider-utils 5.0.17
- 2.0.1630 Jul 2026@ai-sdk/provider-utils 5.0.16
- 2.0.1529 Jul 2026@ai-sdk/provider-utils 5.0.15
- 2.0.1428 Jul 2026@ai-sdk/provider-utils 5.0.14
- 2.0.1327 Jul 2026@ai-sdk/provider 4.0.4@ai-sdk/provider-utils 5.0.13
- 2.0.1221 Jul 2026@ai-sdk/provider-utils 5.0.12
- 2.0.1117 Jul 2026@ai-sdk/provider-utils 5.0.11
- 2.0.1014 Jul 2026@ai-sdk/provider-utils 5.0.10
2.0.9
13 Jul 2026provider-utils: Validate provider-response URLs in
getFromApigetFromApinow has avalidateUrlflag. It is optional so existing callers keep compiling (omitting it behaves likefalse, i.e. no validation), but all AI SDK provider packages set it explicitly at every call site so each one makes a visible trust decision. Whentrue, the URL is routed throughfetchWithValidatedRedirects— the same guard used bydownloadBlob— which rejects private/loopback/link-local targets, re-validates every redirect hop, strips proxy/metadata/cookie request headers, and drops all caller headers except the user-agent on cross-origin redirects (custom API-key headers must not follow a redirect off-origin any more thanAuthorizationmay); blocked URLs throwDownloadError. It is enabled at the image/video/audio download and polling call sites where the URL comes from a provider response body; URLs built from developer-configured endpoints passvalidateUrl: falseand are unaffected.A new optional
credentialedOriginwithholds caller headers unless the URL is same-origin with it, so the API key is not sent to a response-supplied host on a different origin.A new optional
trustedOriginexempts URLs (and redirect hops) that are same-origin with the developer-configured provider endpoint from target validation, so self-hosted and localhost deployments whose response URLs point back at the configured host keep working; all other hops are still validated.Also closes range gaps in
validateDownloadUrl(IPv4224.0.0.0/4multicast and the TEST-NET documentation ranges192.0.2.0/24,198.51.100.0/24,203.0.113.0/24; IPv6 documentation ranges2001:db8::/32and3fff::/20), and follows only the fetch-spec redirect status codes (301/302/303/307/308) — aLocationheader on any other status is not followed. This guard performs string/literal checks only and does not resolve DNS; hostnames that resolve to private addresses and DNS rebinding remain out of scope and must be constrained at the network layer (or by injecting a Nodefetchthat pins the resolved IP at connect time) for server deployments handling untrusted URLs. Seecontributing/secure-url-handling.md.
Patch Changes
provider-utils: Validate provider-response URLs in
getFromApigetFromApinow has avalidateUrlflag. It is optional so existing callers keep compiling (omitting it behaves likefalse, i.e. no validation), but all AI SDK provider packages set it explicitly at every call site so each one makes a visible trust decision. Whentrue, the URL is routed throughfetchWithValidatedRedirects— the same guard used bydownloadBlob— which rejects private/loopback/link-local targets, re-validates every redirect hop, strips proxy/metadata/cookie request headers, and drops all caller headers except the user-agent on cross-origin redirects (custom API-key headers must not follow a redirect off-origin any more thanAuthorizationmay); blocked URLs throwDownloadError. It is enabled at the image/video/audio download and polling call sites where the URL comes from a provider response body; URLs built from developer-configured endpoints passvalidateUrl: falseand are unaffected.A new optional
credentialedOriginwithholds caller headers unless the URL is same-origin with it, so the API key is not sent to a response-supplied host on a different origin.A new optional
trustedOriginexempts URLs (and redirect hops) that are same-origin with the developer-configured provider endpoint from target validation, so self-hosted and localhost deployments whose response URLs point back at the configured host keep working; all other hops are still validated.Also closes range gaps in
validateDownloadUrl(IPv4224.0.0.0/4multicast and the TEST-NET documentation ranges192.0.2.0/24,198.51.100.0/24,203.0.113.0/24; IPv6 documentation ranges2001:db8::/32and3fff::/20), and follows only the fetch-spec redirect status codes (301/302/303/307/308) — aLocationheader on any other status is not followed. This guard performs string/literal checks only and does not resolve DNS; hostnames that resolve to private addresses and DNS rebinding remain out of scope and must be constrained at the network layer (or by injecting a Nodefetchthat pins the resolved IP at connect time) for server deployments handling untrusted URLs. Seecontributing/secure-url-handling.md.
2.0.6 – 2.0.72 releases that only update dependencies@ai-sdk/provider 4.0.3@ai-sdk/provider-utils 5.0.7Show each
2.0.5
2 Jul 2026Add experimental streaming transcription support for transcription models, including OpenAI
gpt-realtime-whisperand xAI WebSocket STT.
Patch Changes
Add experimental streaming transcription support for transcription models, including OpenAI
gpt-realtime-whisperand xAI WebSocket STT.
2.0.1 – 2.0.44 releases that only update dependencies@ai-sdk/provider-utils 5.0.4@ai-sdk/provider 4.0.1Show each
- 2.0.42 Jul 2026@ai-sdk/provider-utils 5.0.4
- 2.0.31 Jul 2026@ai-sdk/provider-utils 5.0.3
- 2.0.230 Jun 2026@ai-sdk/provider 4.0.1@ai-sdk/provider-utils 5.0.2
- 2.0.127 Jun 2026@ai-sdk/provider-utils 5.0.1
2.0.0
25 Jun 2026- Breaking
Remove CommonJS exports from all packages. All packages are now ESM-only (
"type": "module"). Consumers usingrequire()must switch to ESMimportsyntax. - Breaking
Start v7 pre-release
- Breaking
Make provider implementations code patterns more consistent, including renaming certain exported symbols
For all externally exported symbols that were renamed, the old names continue to work via deprecated aliases.
Major Changes
- Breaking
Remove CommonJS exports from all packages. All packages are now ESM-only (
"type": "module"). Consumers usingrequire()must switch to ESMimportsyntax. - Breaking
Start v7 pre-release
- Breaking
Make provider implementations code patterns more consistent, including renaming certain exported symbols
For all externally exported symbols that were renamed, the old names continue to work via deprecated aliases.
Patch Changes
bfl: Remove duplicate parseProviderOptions call in doGenerate
Add AI Gateway hint to provider READMEs
Trigger release for all packages after provenance setup
bfl: Use 'image' field instead of 'input_image' for fill pro model
Only send provider credentials to same-origin response-supplied URLs
Several provider clients followed a URL taken from the provider's API response (a polling/status URL or a final media URL such as
polling_url,urls.get,result_url,result.sample, orvideo.uri) and reused the authenticated headers — or appended?key=<API_KEY>— on that request. Because the host of the response-supplied URL was never validated, the long-lived API key was sent to whatever host the response named (a CDN in the benign case, or an attacker-chosen host if the provider response was tampered with), allowing credential exfiltration.A new
isSameOriginhelper is added to@ai-sdk/provider-utils, and the affected fetches in@ai-sdk/black-forest-labs,@ai-sdk/fireworks,@ai-sdk/replicate,@ai-sdk/gladia,@ai-sdk/fal, and@ai-sdk/googlenow attach credentials only when the followed URL is same-origin with the provider's configured API origin. Requests to a foreign origin are made without the credential.- Breaking
Raise minimum supported Node.js version to 22. Supported versions: 22, 24, and 26.
Trigger initial canary release
Trigger initial beta release
Add workflow serialization support to all provider models.
@ai-sdk/provider-utils: NewserializeModel()helper that extracts only serializable properties from a model instance, filtering out functions and objects containing functions. Third-party provider authors can use this to add workflow support to their own models.All providers:
headersis now optional in provider config types. This is non-breaking — existing code that passesheaderscontinues to work. Custom provider implementations that construct model configs manually can now omitheaders, which is useful when models are deserialized from a workflow step boundary where auth is provided separately.All provider model classes now include
WORKFLOW_SERIALIZEandWORKFLOW_DESERIALIZEstatic methods, enabling them to cross workflow step boundaries without serialization errors.
- 1.x
1.0.77 – 1.0.793 releases that only update dependencies@ai-sdk/provider-utils 4.0.67Show each
- 1.0.7917 Nov 2026@ai-sdk/provider-utils 4.0.67
- 1.0.7810 Nov 2026@ai-sdk/provider-utils 4.0.66
- 1.0.777 Nov 2026@ai-sdk/provider-utils 4.0.65
1.0.76
6 Nov 2026Validate response-supplied Black Forest Labs image and video polling URLs and image downloads, including redirects, to block requests to private destinations outside the configured provider origin. Preserve self-hosted endpoints and withhold credentials from foreign origins and cross-origin redirects.
Poll get_result when a webhook submit response has no polling URL
Setting
webhookUrlmakes Black Forest Labs return a webhook-shaped submit
response withoutpolling_url, which causedgenerateImageto fail response
validation. The submit schema now accepts that response shape, and generation
polls theget_resultendpoint by request id so the call still returns the
image. TransientTask not foundresponses are retried for a short grace
period; a task that never becomes visible now fails with an error naming the
request id instead of a generic poll timeout.
1.0.74 – 1.0.752 releases that only update dependencies@ai-sdk/provider-utils 4.0.64Show each
- 1.0.753 Nov 2026@ai-sdk/provider-utils 4.0.64
- 1.0.7429 Oct 2026@ai-sdk/provider-utils 4.0.63
1.0.73
21 Oct 2026Defer validation schema construction until first use to reduce provider import time.
Patch Changes
Defer validation schema construction until first use to reduce provider import time.
1.0.72
16 Oct 2026Default unknown image model IDs to the latest supported FLUX image API, currently FLUX 3 Image Klein, while retaining older families' request formats and the original FLUX 3 Image controls. Forward resolution tiers and reference images using the supported API fields, preserve exact dimensions, seed, output format and steps, and support the documented 0–7 safety tolerance range for FLUX 3 Image models.
Patch Changes
Default unknown image model IDs to the latest supported FLUX image API, currently FLUX 3 Image Klein, while retaining older families' request formats and the original FLUX 3 Image controls. Forward resolution tiers and reference images using the supported API fields, preserve exact dimensions, seed, output format and steps, and support the documented 0–7 safety tolerance range for FLUX 3 Image models.
1.0.69 – 1.0.713 releases that only update dependencies@ai-sdk/provider 3.0.19@ai-sdk/provider-utils 4.0.60Show each
- 1.0.7115 Oct 2026@ai-sdk/provider 3.0.19@ai-sdk/provider-utils 4.0.60
- 1.0.7015 Oct 2026@ai-sdk/provider-utils 4.0.59
- 1.0.6913 Oct 2026@ai-sdk/provider-utils 4.0.58
1.0.68
5 Oct 2026Add FLUX 3 image generation and editing support with resolution, grounding, and version options. Handle reasoning and generating poll statuses, stop on terminal task failures, and download signed image URLs without API credentials.
Normalize size-derived aspect ratios to the accepted FLUX 3 values and omit unsupported ratios with a warning. Preserve provider and request headers for image downloads on a custom base URL's origin.
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.