@ai-sdk/fireworks
3.0.97 · 17 Nov 2026Apache-2.0936k / weekRepositoryHomepagenpmAtom feed
314 stable releases, newest first, by release line. Notes are quoted as the maintainers published them.
3.0.97
17 Nov 2026Only updates dependencies:@ai-sdk/provider 4.0.39@ai-sdk/provider-utils 5.0.82@ai-sdk/openai-compatible 3.0.93
3.0.96
13 Nov 2026Derive known model ID suggestions from each provider's model catalog declarations so catalog updates automatically update autocomplete, while preserving existing suggestions, endpoint-specific model lists, and support for custom model IDs.
3.0.90 – 3.0.955 releases that only update dependencies@ai-sdk/provider-utils 5.0.81@ai-sdk/openai-compatible 3.0.92@ai-sdk/provider 4.0.38Show each
- 3.0.9513 Nov 2026@ai-sdk/provider-utils 5.0.81@ai-sdk/openai-compatible 3.0.92
- 3.0.9412 Nov 2026@ai-sdk/openai-compatible 3.0.91@ai-sdk/provider-utils 5.0.80@ai-sdk/provider 4.0.38
- 3.0.9310 Nov 2026@ai-sdk/provider-utils 5.0.79@ai-sdk/openai-compatible 3.0.90
- 3.0.9210 Nov 2026@ai-sdk/provider-utils 5.0.78@ai-sdk/openai-compatible 3.0.89
- 3.0.907 Nov 2026@ai-sdk/provider-utils 5.0.76@ai-sdk/openai-compatible 3.0.87@ai-sdk/provider 4.0.37
3.0.89
6 Nov 2026Refactor Fireworks model ID logic into a model catalog that declares capabilities and provider options, and generate provider capability documentation from it. Request behavior is unchanged.
Patch Changes
Refactor Fireworks model ID logic into a model catalog that declares capabilities and provider options, and generate provider capability documentation from it. Request behavior is unchanged.
3.0.86 – 3.0.883 releases that only update dependencies@ai-sdk/provider 4.0.36@ai-sdk/openai-compatible 3.0.85@ai-sdk/provider-utils 5.0.75Show each
3.0.85
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.
3.0.84
29 Oct 2026Map the top-level
reasoningoption consistently across providersProviders now resolve reasoning the same way:
mapReasoningToProviderEffortnow accepts anyreasoningvalue, returns an optionalproviderOptionsEffortunchanged, and rounds levels that are missing from the effort map to the closest supported level.mapReasoningToProviderBudgetmaps'none'to the minimum reasoning budget, always returns a budget, and uses the default percentage for levels missing frombudgetPercentages.OpenAICompatibleChatConfigadds an optionalmapReasoningfunction for mapping the top-levelreasoningoption.
Patch Changes
Map the top-level
reasoningoption consistently across providersProviders now resolve reasoning the same way:
A provider-specific reasoning setting in
providerOptionsis sent unchanged. OpenAI no longer dropsproviderOptions.openai.reasoningEffortvalues that are not in its list for the model, and Fireworks no longer rewritesproviderOptions.fireworks.reasoningEffort. Fireworks also sends top-levelreasoningvalues directly instead of rounding them to'high'at most, except for model families known to reject'none'(GPT-OSS, GLM-5.3, Muse Spark) or'minimal'(Nemotron, Inkling).Otherwise,
reasoningmaps to the closest level the model supports, rounding down, and rounds up only when there is no lower level. For example,'xhigh'now maps to'high'instead of'max'on Anthropic and Bedrock models withoutxhigheffort, and'medium'maps to'low'instead of'high'on DeepSeek, Kimi K3, and Mistral GLM-5.3 models.'none'on a model that cannot disable reasoning maps to the model's lowest level with a compatibility warning, instead of being dropped or sending a request the API rejects. This affects GPT-6 models without'none', xAI grok-4.5 and later, Groq GPT-OSS, Kimi K3, Perplexity, QuiverAI, Bedrock OpenAIgpt-ossmodels, and Gemini 2.5 Pro (minimum thinking budget). Gemini 3 and Anthropic and Bedrockbetween_toolsmappings now emit the compatibility warning too.
mapReasoningToProviderEffortnow accepts anyreasoningvalue, returns an optionalproviderOptionsEffortunchanged, and rounds levels that are missing from the effort map to the closest supported level.mapReasoningToProviderBudgetmaps'none'to the minimum reasoning budget, always returns a budget, and uses the default percentage for levels missing frombudgetPercentages.OpenAICompatibleChatConfigadds an optionalmapReasoningfunction for mapping the top-levelreasoningoption.
3.0.68 – 3.0.8316 releases that only update dependencies@ai-sdk/provider-utils 5.0.70@ai-sdk/openai-compatible 3.0.80@ai-sdk/provider 4.0.34Show each
- 3.0.8327 Oct 2026@ai-sdk/provider-utils 5.0.70@ai-sdk/openai-compatible 3.0.80
- 3.0.8226 Oct 2026@ai-sdk/provider-utils 5.0.69@ai-sdk/openai-compatible 3.0.79
- 3.0.8124 Oct 2026@ai-sdk/provider 4.0.34@ai-sdk/openai-compatible 3.0.78@ai-sdk/provider-utils 5.0.68
- 3.0.8022 Oct 2026@ai-sdk/provider-utils 5.0.67@ai-sdk/provider 4.0.33@ai-sdk/openai-compatible 3.0.77
- 3.0.7922 Oct 2026@ai-sdk/provider 4.0.32@ai-sdk/openai-compatible 3.0.76@ai-sdk/provider-utils 5.0.66
- 3.0.7821 Oct 2026@ai-sdk/provider-utils 5.0.65@ai-sdk/openai-compatible 3.0.75
- 3.0.7720 Oct 2026@ai-sdk/provider 4.0.31@ai-sdk/provider-utils 5.0.64@ai-sdk/openai-compatible 3.0.74
- 3.0.7619 Oct 2026@ai-sdk/openai-compatible 3.0.73
- 3.0.7519 Oct 2026@ai-sdk/provider 4.0.30@ai-sdk/openai-compatible 3.0.72@ai-sdk/provider-utils 5.0.63
- 3.0.7416 Oct 2026@ai-sdk/provider 4.0.29@ai-sdk/provider-utils 5.0.62@ai-sdk/openai-compatible 3.0.71
- 3.0.7315 Oct 2026@ai-sdk/provider 4.0.28@ai-sdk/openai-compatible 3.0.70@ai-sdk/provider-utils 5.0.61
- 3.0.7215 Oct 2026@ai-sdk/provider-utils 5.0.60@ai-sdk/openai-compatible 3.0.69
- 3.0.7112 Oct 2026@ai-sdk/provider-utils 5.0.59@ai-sdk/provider 4.0.27@ai-sdk/openai-compatible 3.0.68
- 3.0.708 Oct 2026@ai-sdk/openai-compatible 3.0.67@ai-sdk/provider 4.0.26@ai-sdk/provider-utils 5.0.58
- 3.0.698 Oct 2026@ai-sdk/provider 4.0.25@ai-sdk/provider-utils 5.0.57@ai-sdk/openai-compatible 3.0.66
- 3.0.687 Oct 2026@ai-sdk/provider 4.0.24@ai-sdk/openai-compatible 3.0.65@ai-sdk/provider-utils 5.0.56
3.0.67
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 – 3.0.664 releases that only update dependencies@ai-sdk/provider 4.0.22@ai-sdk/provider-utils 5.0.54@ai-sdk/openai-compatible 3.0.63Show each
- 3.0.665 Oct 2026@ai-sdk/provider 4.0.22@ai-sdk/provider-utils 5.0.54@ai-sdk/openai-compatible 3.0.63
- 3.0.6530 Sep 2026@ai-sdk/openai-compatible 3.0.62
- 3.0.6430 Sep 2026@ai-sdk/provider 4.0.21@ai-sdk/provider-utils 5.0.53@ai-sdk/openai-compatible 3.0.61
- 3.0.6330 Sep 2026@ai-sdk/openai-compatible 3.0.60@ai-sdk/provider 4.0.20@ai-sdk/provider-utils 5.0.52
3.0.62
28 Sep 2026Use standards-compliant User-Agent header
Patch Changes
Use standards-compliant User-Agent header
3.0.61
28 Sep 2026provider: 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
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.
3.0.56 – 3.0.604 releases that only update dependencies@ai-sdk/provider-utils 5.0.49@ai-sdk/openai-compatible 3.0.57@ai-sdk/provider 4.0.18Show each
- 3.0.6025 Sep 2026@ai-sdk/provider-utils 5.0.49@ai-sdk/openai-compatible 3.0.57
- 3.0.5823 Sep 2026@ai-sdk/provider-utils 5.0.47@ai-sdk/openai-compatible 3.0.55
- 3.0.5723 Sep 2026@ai-sdk/provider 4.0.18@ai-sdk/openai-compatible 3.0.54@ai-sdk/provider-utils 5.0.46
- 3.0.5618 Sep 2026@ai-sdk/provider-utils 5.0.45@ai-sdk/openai-compatible 3.0.53
3.0.55
18 Sep 2026black-forest-labs: Enforce wall-clock image polling deadlines
Patch Changes
black-forest-labs: Enforce wall-clock image polling deadlines
3.0.54
16 Sep 2026Only updates dependencies:@ai-sdk/provider-utils 5.0.43@ai-sdk/provider 4.0.17@ai-sdk/openai-compatible 3.0.51
3.0.53
16 Sep 2026Keep default Node.js downloads protected by DNS validation and connection pinning when frameworks or instrumentation wrap global fetch before or after the SDK loads.
Patch Changes
Keep default Node.js downloads protected by DNS validation and connection pinning when frameworks or instrumentation wrap global fetch before or after the SDK loads.
3.0.46 – 3.0.527 releases that only update dependencies@ai-sdk/provider 4.0.15@ai-sdk/openai-compatible 3.0.49@ai-sdk/provider-utils 5.0.41Show each
- 3.0.5215 Sep 2026@ai-sdk/provider 4.0.15@ai-sdk/openai-compatible 3.0.49@ai-sdk/provider-utils 5.0.41
- 3.0.5111 Sep 2026@ai-sdk/provider 4.0.14@ai-sdk/provider-utils 5.0.40@ai-sdk/openai-compatible 3.0.48
- 3.0.509 Sep 2026@ai-sdk/provider 4.0.13@ai-sdk/openai-compatible 3.0.47@ai-sdk/provider-utils 5.0.39
- 3.0.499 Sep 2026@ai-sdk/provider 4.0.12@ai-sdk/openai-compatible 3.0.46@ai-sdk/provider-utils 5.0.38
- 3.0.488 Sep 2026@ai-sdk/provider 4.0.11@ai-sdk/provider-utils 5.0.37@ai-sdk/openai-compatible 3.0.45
- 3.0.474 Sep 2026@ai-sdk/openai-compatible 3.0.44
- 3.0.462 Sep 2026@ai-sdk/provider-utils 5.0.36@ai-sdk/openai-compatible 3.0.43
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.