@ai-sdk/openai-compatible
3.0.93 · 17 Nov 2026Apache-2.014.4M / weekRepositoryHomepagenpmAtom feed
300 stable releases, newest first, by release line. Notes are quoted as the maintainers published them.
- 2.x
2.0.34 – 2.0.352 releases that only update dependencies@ai-sdk/provider-utils 4.0.19Show each
- 2.0.355 Mar 2026@ai-sdk/provider-utils 4.0.19
- 2.0.345 Mar 2026@ai-sdk/provider-utils 4.0.18
2.0.33
2 Mar 2026openai-compat: Decode base64 string data
2.0.30 – 2.0.323 releases that only update dependencies@ai-sdk/provider-utils 4.0.17Show each
- 2.0.322 Mar 2026@ai-sdk/provider-utils 4.0.17
- 2.0.3128 Feb 2026@ai-sdk/provider-utils 4.0.16
- 2.0.3012 Feb 2026@ai-sdk/provider-utils 4.0.15
2.0.29
11 Feb 2026Normalize provider specific model options type names and ensure they are exported
2.0.28
6 Feb 2026Only updates dependencies:@ai-sdk/provider 3.0.8@ai-sdk/provider-utils 4.0.14
2.0.27
4 Feb 2026Change usage schemas from z.object to z.looseObject to improve compatibility with non-standard OpenAI-compatible APIs.
2.0.21 – 2.0.266 releases with no change for you4 dependency updates, 2 maintenance@ai-sdk/provider 3.0.7@ai-sdk/provider-utils 4.0.13Show each
- 2.0.261 Feb 2026@ai-sdk/provider 3.0.7@ai-sdk/provider-utils 4.0.13
- 2.0.2531 Jan 2026@ai-sdk/provider-utils 4.0.12
- 2.0.2429 Jan 2026@ai-sdk/provider-utils 4.0.11@ai-sdk/provider 3.0.6
- 2.0.2329 Jan 2026docs, tests or tooling
- 2.0.2229 Jan 2026docs, tests or tooling
- 2.0.2127 Jan 2026@ai-sdk/provider-utils 4.0.10
2.0.20
27 Jan 2026openai-compatible: Include reasoning_content in assistant messages for multi-turn tool calls
2.0.19
26 Jan 2026openai-compat: Add metadata extractor to provider settings
2.0.17 – 2.0.182 releases with no change for you1 dependency update, 1 maintenance@ai-sdk/provider 3.0.5@ai-sdk/provider-utils 4.0.9Show each
- 2.0.1822 Jan 2026@ai-sdk/provider 3.0.5@ai-sdk/provider-utils 4.0.9
- 2.0.1722 Jan 2026docs, tests or tooling
2.0.16
20 Jan 2026openai-compatible: Accept non-OpenAI provider options
2.0.15
20 Jan 2026- Deprecated
Use consistent camelCase
openaiCompatiblekey for providerOptions. The kebab-caseopenai-compatiblekey is now deprecated but still supported with a console warning.
2.0.14
20 Jan 2026openai-compat: Support passing multiple file types
2.0.13
16 Jan 2026Only updates dependencies:@ai-sdk/provider 3.0.4@ai-sdk/provider-utils 4.0.8
2.0.12
15 Jan 2026openai-compatible: Add transformRequestBody function for openai-compatible
2.0.10 – 2.0.112 releases that only update dependencies@ai-sdk/provider-utils 4.0.7@ai-sdk/provider 3.0.3Show each
2.0.9
13 Jan 2026groq,compat: Add strictJsonSchema for providers
2.0.8
13 Jan 2026compat,groq: Send reasoning-end before text-start in streaming
2.0.7
12 Jan 2026openai-compat: Add thoughtSignature handling for google models
2.0.6
12 Jan 2026Only updates a dependency:@ai-sdk/provider-utils 4.0.5
2.0.5
12 Jan 2026Change some response schemas from z.object to z.looseObject to improve compatibility with non-standard OpenAI-compatible APIs.
2.0.3 – 2.0.42 releases that only update dependencies@ai-sdk/provider 3.0.2@ai-sdk/provider-utils 4.0.4Show each
2.0.2
30 Dec 2025Trigger release to update
@latest
Patch Changes
Trigger release to update
@latest
2.0.1
23 Dec 2025Only updates a dependency:@ai-sdk/provider-utils 4.0.1
2.0.0
22 Dec 2025- Breaking
Ai SDK 6 beta
provider: Add specificationVersion to ProviderV3
provider: Shared spec v3
Major Changes
- Breaking
Ai SDK 6 beta
Patch Changes
provider: Add specificationVersion to ProviderV3
provider: Shared spec v3
feat(openai); update spec for mcp approval
Add textVerbosity provider option support
EmbeddingModelV3Tool execution approval
Provider-V3Extended token usage
LanguageModelV3Image editing
ImageModelV3Expose raw finish reason
Moved dependency
@ai-sdk/test-serverto devDependenciestool-specific strict mode
- 1.x
1.0.63
10 Nov 2026Only updates a dependency:@ai-sdk/provider-utils 3.0.46
1.0.62
7 Nov 2026Avoid empty structured-output answers from Baseten's DeepSeek V4 Pro 0813 when reasoning is enabled. Fall back to JSON prompt instructions while keeping reasoning and SDK output validation, and report the fallback through request transformation warnings.
openai,openai-compatible: Surface refusal logprobs and openai-compatible refusals
@ai-sdk/openai: Chat Completions responses that contain a refusal can returnlogprobs.refusalnext tologprobs.content. The provider previously read onlylogprobs.content, soproviderMetadata.openai.logprobswas empty or missing for refusals. Refusal logprobs are now included in emission order (content logprobs followed by refusal logprobs) in bothgenerateTextandstreamText.Streaming logprobs are now collected across all chunks in
streamText: previously only the logprobs of the last streamed chunk were reported. This applies to content logprobs as well, soproviderMetadata.openai.logprobsnow contains the logprobs of every streamed token instead of only the last chunk's tokens. Explicitly empty logprobs (logprobs: { content:, refusal: null }) are reported as an empty array, as before.A refusal that arrives in the same streamed chunk as the
finish_reasonis now taken into account: such a response is reported with acontent-filterfinish reason instead ofstop.@ai-sdk/openai-compatible: Chat Completions responses that carrymessage.refusal(non-streaming) ordelta.refusal(streaming) were ignored, so providers such as OpenAI served throughcreateOpenAICompatiblelost the refusal text and reported an emptystopresponse. Refusals are now returned as text content after any content text, and a non-empty refusal with astopfinish reason is reported as acontent-filterfinish reason. This also applies when the refusal and the finish reason arrive in the same streamed chunk. Non-string refusals (for examplerefusal: falsefrom servers that use booleans) are ignored instead of failing the response.
Patch Changes
Avoid empty structured-output answers from Baseten's DeepSeek V4 Pro 0813 when reasoning is enabled. Fall back to JSON prompt instructions while keeping reasoning and SDK output validation, and report the fallback through request transformation warnings.
openai,openai-compatible: Surface refusal logprobs and openai-compatible refusals
@ai-sdk/openai: Chat Completions responses that contain a refusal can returnlogprobs.refusalnext tologprobs.content. The provider previously read onlylogprobs.content, soproviderMetadata.openai.logprobswas empty or missing for refusals. Refusal logprobs are now included in emission order (content logprobs followed by refusal logprobs) in bothgenerateTextandstreamText.Streaming logprobs are now collected across all chunks in
streamText: previously only the logprobs of the last streamed chunk were reported. This applies to content logprobs as well, soproviderMetadata.openai.logprobsnow contains the logprobs of every streamed token instead of only the last chunk's tokens. Explicitly empty logprobs (logprobs: { content:, refusal: null }) are reported as an empty array, as before.A refusal that arrives in the same streamed chunk as the
finish_reasonis now taken into account: such a response is reported with acontent-filterfinish reason instead ofstop.@ai-sdk/openai-compatible: Chat Completions responses that carrymessage.refusal(non-streaming) ordelta.refusal(streaming) were ignored, so providers such as OpenAI served throughcreateOpenAICompatiblelost the refusal text and reported an emptystopresponse. Refusals are now returned as text content after any content text, and a non-empty refusal with astopfinish reason is reported as acontent-filterfinish reason. This also applies when the refusal and the finish reason arrive in the same streamed chunk. Non-string refusals (for examplerefusal: falsefrom servers that use booleans) are ignored instead of failing the response.
1.0.61
3 Nov 2026openai-compatible: Preserve string tool call arguments and safely serialize BigInt and circular structures in tool calls and outputs
Patch Changes
openai-compatible: Preserve string tool call arguments and safely serialize BigInt and circular structures in tool calls and outputs
1.0.60
30 Oct 2026Only updates a dependency:@ai-sdk/provider-utils 3.0.43
1.0.59
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.
1.0.58
30 Sep 2026Only updates a dependency:@ai-sdk/provider-utils 3.0.41
1.0.57
28 Sep 2026provider-utils: Preserve streamed tool calls with unreliable IDs and indices
Patch Changes
provider-utils: Preserve streamed tool calls with unreliable IDs and indices
1.0.55 – 1.0.562 releases that only update dependencies@ai-sdk/provider-utils 3.0.39@ai-sdk/provider 2.0.5Show each
1.0.54
9 Sep 2026openai: Return an AI SDK error for empty chat completion choices
Patch Changes
openai: Return an AI SDK error for empty chat completion choices
1.0.48 – 1.0.534 releases that only update dependencies@ai-sdk/provider-utils 3.0.36Show each
- 1.0.5331 Aug 2026@ai-sdk/provider-utils 3.0.36
- 1.0.5226 Aug 2026@ai-sdk/provider-utils 3.0.35
- 1.0.4924 Aug 2026@ai-sdk/provider-utils 3.0.33
- 1.0.4811 Aug 2026@ai-sdk/provider-utils 3.0.32
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.