NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
npm · #1825 most downloaded on npm
Last release today
16 Sep 2026
Ships on a steady schedule
a new release about every 2 weeks
Most releases are documented
notes for 52 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
2 years old
181 releases · first in 2024
### Patch Changes - 9061dc0: feat: image editing
366f50b: chore(provider): add deprecated textEmbeddingModel and textEmbedding aliases
One column per month.
3bd2689: feat: extended token usage
53f3368: feat(provider): support embedding model call warnings in specification
dce03c4: feat: tool input examples
1bd7d32: feat: tool-specific strict mode
544d4e8: chore(specification): rename v3 provider defined tool to provider tool
954c356: feat(openai): allow custom names for provider-defined tools
457318b: chore(provider,ai): switch to SharedV3Warning and unified warnings
8d9e8ad: chore(provider): remove generics from EmbeddingModelV3
8d9e8ad: chore(provider): remove generics from EmbeddingModelV3
Before
model.textEmbeddingModel("my-model-id");
After
model.embeddingModel("my-model-id");
10d819b: fix(packages/provider): fix CallWarning and allow strings as type
db913bd: fix(google): add thought signature to gemini 3 pro image parts
b681d7d: feat: expose usage tokens for 'generateImage' function
bb36798: fix(spec): LanguageModelV3ToolResult["result"] change from unknown to NonNullable
LanguageModelV3ToolResult["result"] change from unknown to NonNullable<JSONValue>af3780b: chore(provider): remove providerExecuted from LanguageModelV3ToolResult
37c58a0: This release introduces wrapEmbeddingModel, a new helper that brings embedding model customization capabilities similar to wrapLanguageModel.
wrapEmbeddingModel, a new helper that brings embedding model customization capabilities similar to wrapLanguageModel.### Patch Changes - d1bdadb: Added reranking model
4c44a5b: fix(spec): allow undefined values in JSONObject type
undefined values in JSONObject type0c3b58b: fix(provider): add specificationVersion to ProviderV3
a755db5: feat(provider): Add SharedV3Warning type
3794514: feat: flexible tool output content support
81d4308: feat: provider-executed dynamic tools
### Major Changes - dee8b05: ai SDK 6 beta
046aa3b: feat(provider): speech model v3 spec
0adc679: feat(provider): shared spec v3
### Patch Changes - 8dac895: feat: LanguageModelV3
LanguageModelV3### Patch Changes - ed329cb: feat: Provider-V3 - 522f6b8: feat: ImageModelV3
Provider-V3ImageModelV30c4822d: feat: EmbeddingModelV3
EmbeddingModelV378928cb: release: start 5.1 beta
Nothing published for this version
Updated dependencies [ f3c1980 ]
Nothing published for this version
@ai-sdk/openai-compatible@2.0.68
5604dde : feat(zai): add the Z.AI provider with GLM chat completions, streaming, reasoning, tools, and multimodal inputs
dc714f3: release alpha.4
b5da06a: update to LanguageModelV2ProviderDefinedClientTool to add server side tool later on
48d257a: release alpha.15
0d2c085: chore (provider): tweak provider definition
9222aeb: release alpha.8
e2aceaf: feat: add raw chunk support
7b3ae3f: chore (provider): change getSupportedUrls to supportedUrls (language model v2)
a166433: feat: add transcription with experimental_transcribe
26735b5: chore(embedding-model): add v2 interface
443d8ec: feat(embedding-model-v2): add response body field
a8c8bd5: feat(embed-many): respect supportsParallelCalls & concurrency
9bf7291: chore(providers/openai): enable structuredOutputs by default & switch to provider option
2e13791: feat(anthropic): add server-side web search support
472524a: spec (ai): add provider options to tools
dd3ff01: chore: add language setting to speechv2
9301f86: refactor (image-model): rename ImageModelV1 to ImageModelV2
0a87932: core (ai): change transcription model mimeType to mediaType
c4a2fec: chore (provider): extract shared provider options and metadata (spec)
79457bd: chore (provider): extract LanguageModelV2File
8aa9e20: feat: add speech with experimental_generateSpeech
4617fab: chore(embedding-models): remove remaining settings
cb68df0: feat: add transcription and speech model support to provider registry
ad80501: chore (provider): allow both binary and base64 file content (spec)
Before
import { convertUint8ArrayToBase64 } from "@ai-sdk/provider-utils";
// Had to manually convert binary data to base64
const fileData = new Uint8Array([0, 1, 2, 3]);
const filePart = {
type: "file",
mediaType: "application/pdf",
data: convertUint8ArrayToBase64(fileData), // Required conversion
};
After
// Can use binary data directly
const fileData = new Uint8Array([0, 1, 2, 3]);
const filePart = {
type: "file",
mediaType: "application/pdf",
data: fileData, // Direct Uint8Array support
};
68ecf2f: release alpha.13
6b98118: release alpha.3
3f2f00c: feat: ImageModelV2#maxImagesPerCall can be set to a function that returns a number or undefined, optionally as a promise
pull request: https://github.com/vercel/ai/pull/6343
9bd5ab5: feat (provider): add providerMetadata to ImageModelV2 interface (#5977)
The experimental_generateImage method from the ai package now returnes revised prompts for OpenAI's image models.
const prompt = "Santa Claus driving a Cadillac";
const { providerMetadata } = await experimental_generateImage({
model: openai.image("dall-e-3"),
prompt,
});
const revisedPrompt = providerMetadata.openai.images[0]?.revisedPrompt;
console.log({
prompt,
revisedPrompt,
});
5c56081: release alpha.7
fd65bc6: chore(embedding-model-v2): rename rawResponse to response
26535e0: release alpha.2
393138b: feat(embedding-model-v2): add providerOptions
7182d14: Remove Experimental_LanguageModelV2Middleware type
c1e6647: release alpha.11
811dff3: release alpha.9
f10304b: feat(tool-calling): don't require the user to have to pass parameters
27deb4d: feat (provider/gateway): Add providerMetadata to embeddings response
c4df419: release alpha.10
7979f7f: feat (provider): support reasoning tokens, cached input tokens, total token in usage information
9bd5ab5: feat (provider): add providerMetadata to ImageModelV2 interface
9bd5ab5: feat (provider): add providerMetadata to ImageModelV2 interface (#5977)
The experimental_generateImage method from the ai package now returnes revised prompts for OpenAI's image models.
const prompt = "Santa Claus driving a Cadillac";
const { providerMetadata } = await experimental_generateImage({
model: openai.image("dall-e-3"),
prompt,
});
const revisedPrompt = providerMetadata.openai.images[0]?.revisedPrompt;
console.log({
prompt,
revisedPrompt,
});
7b3ae3f: chore (provider): change getSupportedUrls to supportedUrls (language model v2)
e030615: chore (provider): remove prompt type from language model v2 spec
a3f768e: chore: restructure reasoning support
ImageModelV1 to ImageModelV2e86be6f: chore: remove logprobs
95857aa: chore: restructure language model supported urls
b6b43c7: chore: move warnings into stream-start part (spec)
14c9410: chore: refactor file towards source pattern (spec)
Experimental_LanguageModelV2Middleware type411e483: chore (provider): refactor usage (language model v2)
6f6bb89: chore (provider): cleanup request and rawRequest (language model v2)
d1a1aa1: chore (provider): merge rawRequest into request (language model v2)
abf9a79: chore: rename mimeType to mediaType
c57e248: chore (provider): remove mode
### Major Changes - d5f588f: AI SDK 5
27deb4d: feat (provider/gateway): Add providerMetadata to embeddings response
742b7be: feat: forward id, streaming start, streaming end of content blocks
### Patch Changes - 48d257a: release alpha.15
63f9e9b: chore (provider,ai): tools have input/output instead of args,result
### Patch Changes - 68ecf2f: release alpha.13
e2aceaf: feat: add raw chunk support
### Patch Changes - c1e6647: release alpha.11
### Patch Changes - c4df419: release alpha.10
### Patch Changes - 811dff3: release alpha.9
### Patch Changes - 9222aeb: release alpha.8
### Patch Changes - 5c56081: release alpha.7
Your coding agent can read these notes before it upgrades. Set up the MCP server →