@ai-sdk/gateway
4.0.121 · 21 Oct 2026Apache-2.017.5M / weekRepositoryHomepagenpmAtom feed
541 stable releases, newest first, by release line. Notes are quoted as the maintainers published them.
4.0.119
20 Oct 20269d13c4d: Add the MiniMax M3.1 Flash model ID to the MiniMax and AI Gateway providers.
0c2a9de: Add
maxOutputTokensandreasoningto experimental decision calls and forward them to language-model-backed decisions. Language-model adapters keep reasoning disabled when omitted. Native decision providers warn when either setting is unsupported.
Patch Changes
9d13c4d: Add the MiniMax M3.1 Flash model ID to the MiniMax and AI Gateway providers.
0c2a9de: Add
maxOutputTokensandreasoningto experimental decision calls and forward them to language-model-backed decisions. Language-model adapters keep reasoning disabled when omitted. Native decision providers warn when either setting is unsupported.
4.0.116
16 Oct 2026Only updates dependencies:@ai-sdk/provider 4.0.29@ai-sdk/provider-utils 5.0.62
4.0.111 – 4.0.1122 releases that only update dependencies@ai-sdk/provider-utils 5.0.59@ai-sdk/provider 4.0.27Show each
- 4.0.11213 Oct 2026dependency updates
- 4.0.11112 Oct 2026@ai-sdk/provider-utils 5.0.59@ai-sdk/provider 4.0.27
4.0.109
8 Oct 20264.0.108
8 Oct 20269184a35: Add ordered text, file, and JSON parts to experimental decision state. Support image input in OpenAI Decisions and language model adapters. Gateway retains its existing string and JSON request format and rejects files, as does TypeSafe AI.
Arrays passed directly as state now contain decision state parts. Wrap JSON arrays in an object or a json part.
Normalize all public state forms into an array of parts before calling decision providers. Providers receive text and JSON objects as text and json parts.
Serialize decision file bytes as base64 in OpenTelemetry state attributes. Model-call spans record normalized state parts, while outer spans retain public state inputs.
Preserve native JSON state in TypeSafe AI when state contains one JSON part. Label shared state in language-model decision prompts.
Patch Changes
9184a35: Add ordered text, file, and JSON parts to experimental decision state. Support image input in OpenAI Decisions and language model adapters. Gateway retains its existing string and JSON request format and rejects files, as does TypeSafe AI.
Arrays passed directly as state now contain decision state parts. Wrap JSON arrays in an object or a json part.
Normalize all public state forms into an array of parts before calling decision providers. Providers receive text and JSON objects as text and json parts.
Serialize decision file bytes as base64 in OpenTelemetry state attributes. Model-call spans record normalized state parts, while outer spans retain public state inputs.
Preserve native JSON state in TypeSafe AI when state contains one JSON part. Label shared state in language-model decision prompts.
4.0.105
6 Oct 20264.0.104
5 Oct 20264.0.102
30 Sep 20268c65988: feat(ai): add telemetry to speech generation and transcription, including provider usage propagation and experimental streaming lifecycle callbacks
e25994e: fix(gateway): scope
getCredits()toteamIdOrSlugThe credits endpoint reads the team from the
teamId/slugquery parameter rather than thex-vercel-ai-gateway-teamheader.getCredits()now forwards the configured team as a query parameter, so credentials that can access multiple teams (such as Vercel access tokens) are no longer rejected with an authentication error.e74afc5: chore(provider/gateway): update gateway model settings files
Patch Changes
8c65988: feat(ai): add telemetry to speech generation and transcription, including provider usage propagation and experimental streaming lifecycle callbacks
e25994e: fix(gateway): scope
getCredits()toteamIdOrSlugThe credits endpoint reads the team from the
teamId/slugquery parameter rather than thex-vercel-ai-gateway-teamheader.getCredits()now forwards the configured team as a query parameter, so credentials that can access multiple teams (such as Vercel access tokens) are no longer rejected with an authentication error.e74afc5: chore(provider/gateway): update gateway model settings files
4.0.97
28 Sep 2026Only updates dependencies:@ai-sdk/provider-utils 5.0.50@ai-sdk/provider 4.0.19
4.0.94
25 Sep 2026Only updates a dependency:@ai-sdk/provider-utils 5.0.49
4.0.91
23 Sep 20262693319: Add Gemini 3.8 TTS support with structured speech metadata and per-turn speaker and style controls for prebuilt voices. Preserve native WAV responses without adding a second header, support explicit raw PCM, mu-law, and A-law output, and identify headerless audio formats correctly. Add the Gemini 3.8 speech model IDs to Google and Gateway types.
Share transcript and custom-voice inspection through the Google provider internal export, and reject empty speech transcripts before sending a request. Default newer and custom model IDs to structured speech while preserving the legacy format for Gemini 2.5 and 3.1.
b73f2f9: feat(provider/gateway): add quantization conditions to the has provider option
Patch Changes
2693319: Add Gemini 3.8 TTS support with structured speech metadata and per-turn speaker and style controls for prebuilt voices. Preserve native WAV responses without adding a second header, support explicit raw PCM, mu-law, and A-law output, and identify headerless audio formats correctly. Add the Gemini 3.8 speech model IDs to Google and Gateway types.
Share transcript and custom-voice inspection through the Google provider internal export, and reject empty speech transcripts before sending a request. Default newer and custom model IDs to structured speech while preserving the legacy format for Gemini 2.5 and 3.1.
b73f2f9: feat(provider/gateway): add quantization conditions to the has provider option
4.0.88
21 Sep 202620dd00a: feat(provider/gateway): support
reasoningandtool-useinhasmodel filtering7cf7cee: feat(xai): add grok 4.7 model ID
c42576a: feat(gateway): support cancelling batches with
experimental_cancelBatch
Patch Changes
20dd00a: feat(provider/gateway): support
reasoningandtool-useinhasmodel filtering7cf7cee: feat(xai): add grok 4.7 model ID
c42576a: feat(gateway): support cancelling batches with
experimental_cancelBatchd85dcf5: chore(provider/gateway): update gateway model settings files
fd9b3f3: chore(provider/gateway): update gateway model settings files
4.0.87
18 Sep 2026Only updates a dependency:@ai-sdk/provider-utils 5.0.45
4.0.84
16 Sep 2026Only updates dependencies:@ai-sdk/provider-utils 5.0.43@ai-sdk/provider 4.0.17
4.0.83
16 Sep 20264.0.82
15 Sep 2026Only updates dependencies:@ai-sdk/provider 4.0.15@ai-sdk/provider-utils 5.0.41
4.0.80
12 Sep 20267f76d83: fix(gateway): forward server-returned warnings on language model doGenerate
generateText(...).warningsthrough the gateway provider was always an empty array:doGeneratespread the gateway response body and then overwrote the server'swarningswith a locally constructed empty array. The warnings the gateway relays from the upstream provider (and gateway-originated warnings) are now forwarded, matching the streaming path and every other modality.
4.0.79
11 Sep 20264.0.78
9 Sep 2026Only updates dependencies:@ai-sdk/provider 4.0.13@ai-sdk/provider-utils 5.0.39
4.0.77
9 Sep 20264.0.76
8 Sep 20264.0.71
1 Sep 2026Only updates dependencies:@ai-sdk/provider 4.0.10@ai-sdk/provider-utils 5.0.35