@ai-sdk/openai-compatible
3.0.93 · 17 Nov 2026Apache-2.014M / weekRepositoryHomepagenpmAtom feed
299 stable releases, newest first, by release line. Notes are quoted as the maintainers published them.
3.0.92 – 3.0.932 releases that only update dependencies@ai-sdk/provider 4.0.39@ai-sdk/provider-utils 5.0.82Show each
3.0.91
12 Nov 2026Forward the provider's configured fetch transport when downloading file inputs. Add a
fetchoption tocreateDownloadso core downloads can also useguarded-fetchfor opt-in DNS validation on Node.js. The function returned bycreateDownloadcan now also be passed asexperimental_downloadtogenerateTextandstreamText, andexperimental_downloadnow also handles generated file URLs returned by the model, so one hook covers all core downloads. Document that the default URL checks do not resolve DNS and recommend the guarded transport or network egress controls for untrusted URLs.Keep Azure image and Vertex tool-result downloads separate from provider authentication wrappers so file hosts never receive Azure bearer tokens or Vertex Express Mode API keys.
Pass the call's abort signal to custom download requests, including prompt assets and generated files, so
experimental_download: createDownload({ fetch })preserves cancellation and timeouts.
Patch Changes
Forward the provider's configured fetch transport when downloading file inputs. Add a
fetchoption tocreateDownloadso core downloads can also useguarded-fetchfor opt-in DNS validation on Node.js. The function returned bycreateDownloadcan now also be passed asexperimental_downloadtogenerateTextandstreamText, andexperimental_downloadnow also handles generated file URLs returned by the model, so one hook covers all core downloads. Document that the default URL checks do not resolve DNS and recommend the guarded transport or network egress controls for untrusted URLs.Keep Azure image and Vertex tool-result downloads separate from provider authentication wrappers so file hosts never receive Azure bearer tokens or Vertex Express Mode API keys.
Pass the call's abort signal to custom download requests, including prompt assets and generated files, so
experimental_download: createDownload({ fetch })preserves cancellation and timeouts.
3.0.89 – 3.0.902 releases that only update dependencies@ai-sdk/provider-utils 5.0.79Show each
- 3.0.9010 Nov 2026@ai-sdk/provider-utils 5.0.79
- 3.0.8910 Nov 2026@ai-sdk/provider-utils 5.0.78
3.0.87
7 Nov 2026Add
resolveProviderOptionsto parse provider options that a model accepts under severalproviderOptionskeys, either as aliases (first) or merged in order (merge), and use it for the existing multi-key lookups in the OpenAI, OpenAI-compatible, Anthropic, Google, and Amazon Bedrock models. Resolution behavior for these models is unchanged.
Patch Changes
Add
resolveProviderOptionsto parse provider options that a model accepts under severalproviderOptionskeys, either as aliases (first) or merged in order (merge), and use it for the existing multi-key lookups in the OpenAI, OpenAI-compatible, Anthropic, Google, and Amazon Bedrock models. Resolution behavior for these models is unchanged.
3.0.86
6 Nov 2026Refactor OpenAI Compatible model ID logic into a model catalog that declares capabilities and provider options, and generate provider capability documentation from it. Request behavior is unchanged.
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.
3.0.85
5 Nov 2026openai-compatible: Keep raw
verbosityprovider option whentextVerbosityis not setPreviously, an unset
textVerbosityalways wroteverbosity: undefinedto the request body, which silently dropped a rawverbositypassed through provider options.verbosityis now only written fromtextVerbositywhen it has a value;textVerbositystill takes precedence when both are set.Accept inline text file data as text content, matching text files supplied as bytes or base64.
Patch Changes
openai-compatible: Keep raw
verbosityprovider option whentextVerbosityis not setPreviously, an unset
textVerbosityalways wroteverbosity: undefinedto the request body, which silently dropped a rawverbositypassed through provider options.verbosityis now only written fromtextVerbositywhen it has a value;textVerbositystill takes precedence when both are set.Accept inline text file data as text content, matching text files supplied as bytes or base64.
3.0.84
3 Nov 2026Only updates a dependency:@ai-sdk/provider-utils 5.0.74
3.0.83
2 Nov 2026openai-compatible: Preserve string tool call arguments and safely serialize BigInt and circular structures in tool calls and outputs
openai-compatible: Send
reasoningEffort: nullas"reasoning_effort": null, and stop an unsetreasoningEffortfrom overwriting a rawreasoning_effortprovider option
Patch Changes
openai-compatible: Preserve string tool call arguments and safely serialize BigInt and circular structures in tool calls and outputs
openai-compatible: Send
reasoningEffort: nullas"reasoning_effort": null, and stop an unsetreasoningEffortfrom overwriting a rawreasoning_effortprovider option
3.0.82
30 Oct 2026Support 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.
The experimental OpenAI Live
getServerWebSocketConfig()method can now resolve asynchronously. Await its result before using the connection settings.
Patch Changes
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.
The experimental OpenAI Live
getServerWebSocketConfig()method can now resolve asynchronously. Await its result before using the connection settings.
3.0.80 – 3.0.812 releases that only update dependencies@ai-sdk/provider-utils 5.0.71Show each
- 3.0.8129 Oct 2026@ai-sdk/provider-utils 5.0.71
- 3.0.8027 Oct 2026@ai-sdk/provider-utils 5.0.70
3.0.79
26 Oct 2026Fix string interpolation in Amazon Bedrock unsupported provider tool warnings and OpenAI / OpenAI-compatible completion errors for unexpected system messages.
Patch Changes
Fix string interpolation in Amazon Bedrock unsupported provider tool warnings and OpenAI / OpenAI-compatible completion errors for unexpected system messages.
3.0.76 – 3.0.783 releases that only update dependencies@ai-sdk/provider 4.0.34@ai-sdk/provider-utils 5.0.68Show each
3.0.75
21 Oct 2026Defer construction of provider validation schemas until first use to reduce package import time.
Patch Changes
Defer construction of provider validation schemas until first use to reduce package import time.
3.0.74
20 Oct 2026Only updates dependencies:@ai-sdk/provider 4.0.31@ai-sdk/provider-utils 5.0.64
3.0.73
19 Oct 2026openai-compatible, groq, alibaba: Put reasoning before text in doGenerate
3.0.71 – 3.0.722 releases that only update dependencies@ai-sdk/provider 4.0.30@ai-sdk/provider-utils 5.0.63Show each
3.0.70
15 Oct 2026openai-compatible: Support URL-based image responses
Patch Changes
openai-compatible: Support URL-based image responses
3.0.69
15 Oct 2026Only updates a dependency:@ai-sdk/provider-utils 5.0.60
3.0.68
12 Oct 2026openai-compatible: Support uploaded file references via file_id
Patch Changes
openai-compatible: Support uploaded file references via file_id
3.0.67
8 Oct 2026Map the top level embedding dimensions to provider settings
Patch Changes
Map the top level embedding dimensions to provider settings
3.0.65 – 3.0.662 releases that only update dependencies@ai-sdk/provider 4.0.25@ai-sdk/provider-utils 5.0.57Show each
3.0.64
6 Oct 2026provider: Add a portable
maxreasoning level with native provider mappings, compatibility coercions, and budget-based fallback support.Compatibility notes:
Release classification: This remains a patch changeset under the repository's explicit release policy, which uses patch releases for both fixes and features. The TypeScript source-compatibility caveat for exhaustive consumers is disclosed above. Maintainers can override this classification with a
majorlabel if they decide to align the provider-spec addition with a future AI SDK major release.
Patch Changes
provider: Add a portable
maxreasoning level with native provider mappings, compatibility coercions, and budget-based fallback support.Compatibility notes:
TypeScript source compatibility: Adding
maxwidensLanguageModelV4CallOptions['reasoning']and the derivedReasoningLeveltype. Third-party providers and consumers with exhaustive switches orRecord<ReasoningLevel, ...>mappings must handlemaxbefore upgrading. Ordinary calls using existing reasoning levels remain accepted.Amazon Bedrock: Existing Nova 2 calls using portable
reasoning: 'xhigh'now sendmaxReasoningEffort: 'high'instead of the unsupported'max', and return a compatibility warning. Anthropic and OpenAI Bedrock effort mappings retain their existingxhighbehavior. Partial Bedrock reasoning configurations continue to preserve explicit values and derive missing fields; explicit effort/budget overrides and disabled thinking no longer emit warnings for portable mappings that are not sent.Fireworks: Existing portable
minimalandxhighcalls keep their request mappings tolowandhigh, respectively, and now return compatibility warnings in generation and streaming results. Portablemaxmaps tohighwith the same warning behavior.
Release classification: This remains a patch changeset under the repository's explicit release policy, which uses patch releases for both fixes and features. The TypeScript source-compatibility caveat for exhaustive consumers is disclosed above. Maintainers can override this classification with a
majorlabel if they decide to align the provider-spec addition with a future AI SDK major release.
3.0.63
5 Oct 2026Only updates dependencies:@ai-sdk/provider 4.0.22@ai-sdk/provider-utils 5.0.54
3.0.62
30 Sep 2026openai-compatible: Support multipart tool results for compatible providers
3.0.60 – 3.0.612 releases that only update dependencies@ai-sdk/provider 4.0.21@ai-sdk/provider-utils 5.0.53Show each
3.0.59
28 Sep 2026Use standards-compliant User-Agent header
Patch Changes
Use standards-compliant User-Agent header
3.0.58
28 Sep 2026Fix streamed tool calls with missing, blank, or repeated IDs.
provider: Advertise image model file and mask input support
Use confirmed model IDs for capability declarations so unrecognized model names remain unknown. Include Together AI FLUX.2 Pro and Flex single-image editing, and allow asynchronous capability lookups and middleware overrides to resolve to unknown.
Advertise QuiverAI Arrow 2 and Arrow 2 Telos file-input support, and mark Together AI Gemini image inputs unsupported by the current single-image request mapping.
Patch Changes
Fix streamed tool calls with missing, blank, or repeated IDs.
provider: Advertise image model file and mask input support
Use confirmed model IDs for capability declarations so unrecognized model names remain unknown. Include Together AI FLUX.2 Pro and Flex single-image editing, and allow asynchronous capability lookups and middleware overrides to resolve to unknown.
Advertise QuiverAI Arrow 2 and Arrow 2 Telos file-input support, and mark Together AI Gemini image inputs unsupported by the current single-image request mapping.
3.0.51 – 3.0.576 releases that only update dependencies@ai-sdk/provider-utils 5.0.49@ai-sdk/provider 4.0.18Show each
- 3.0.5725 Sep 2026@ai-sdk/provider-utils 5.0.49
- 3.0.5523 Sep 2026@ai-sdk/provider-utils 5.0.47
- 3.0.5423 Sep 2026@ai-sdk/provider 4.0.18@ai-sdk/provider-utils 5.0.46
- 3.0.5318 Sep 2026@ai-sdk/provider-utils 5.0.45
- 3.0.5218 Sep 2026@ai-sdk/provider-utils 5.0.44
- 3.0.5116 Sep 2026@ai-sdk/provider-utils 5.0.43@ai-sdk/provider 4.0.17
3.0.50
16 Sep 2026openai-compatible: Extract streaming response metadata after placeholder chunks
Patch Changes
openai-compatible: Extract streaming response metadata after placeholder chunks
3.0.47 – 3.0.493 releases that only update dependencies@ai-sdk/provider 4.0.15@ai-sdk/provider-utils 5.0.41Show each
3.0.46
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
3.0.45
8 Sep 2026Only updates dependencies:@ai-sdk/provider 4.0.11@ai-sdk/provider-utils 5.0.37
3.0.44
4 Sep 2026openai-compatible: Keep reasoning streams contiguous when deltas include empty tool call arrays
3.0.42 – 3.0.432 releases that only update dependencies@ai-sdk/provider-utils 5.0.36@ai-sdk/provider 4.0.10Show each
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.