Vercel AI SDK adds Grok 4.3, reasoning effort controls, and image quality model support for xAI
Vercel released version 3.0.97 of its AI SDK's xAI integration, adding support for three new models: Grok 4.3, Grok Build 0.1, and Grok Imagine Image Quality. The update introduces reasoning effort controls with 'none' and 'medium' settings.
Vercel AI SDK adds Grok 4.3, reasoning effort controls, and image quality model support for xAI
Vercel released version 3.0.97 of its AI SDK's xAI integration on June 24, 2024, adding support for three new models and reasoning effort controls.
New models and capabilities
The update adds support for:
- Grok 4.3: xAI's latest text model
- Grok Build 0.1: A new specialized model (specific capabilities not disclosed)
- Grok Imagine Image Quality: An image generation model focused on quality
The integration now supports reasoning effort settings with two options: 'none' and 'medium'. This allows developers to control the computational intensity of model responses, similar to reasoning controls in other models like OpenAI's o1 series.
Technical details
The patch (version 3.0.97) curates the model lineup to match xAI's current offerings. The reasoning effort parameter enables developers to trade off between response speed and depth of reasoning for compatible models.
Pricing for the new models and specific benchmark performance metrics were not disclosed in the release notes.
Integration context
Vercel's AI SDK provides a unified interface for integrating multiple AI providers into applications. The xAI integration allows developers to use Grok models alongside other providers like OpenAI, Anthropic, and Google through a single SDK.
The release is commit ab415f6 with patch changes documented under ticket 9300b02.
What this means
This update positions Vercel's AI SDK as one of the first major developer frameworks to support xAI's expanding model lineup. The addition of reasoning effort controls suggests xAI may be implementing similar capabilities to OpenAI's reasoning models, though the company has not publicly disclosed details about these features. For developers using Vercel's framework, this provides immediate access to Grok 4.3 without waiting for official xAI SDK updates, though integration through third-party SDKs may lag behind features available in xAI's native API.
Related Articles
Claude API and web services restored after 35-minute outage affecting Sonnet and Opus models
Anthropic's Claude services went offline on June 23 at 10:19 AM ET, affecting most models including Sonnet and Opus across all platforms except Claude for Government. The company deployed a fix by 10:53 AM ET, ending an outage that lasted approximately 35 minutes.
Mistral AI launches Connectors in Studio with MCP protocol integration and direct tool calling
Mistral AI has released Connectors in Studio, allowing developers to integrate custom MCP (Model Context Protocol) servers and built-in connectors via API/SDK. The release includes direct tool calling for deterministic workflows and human-in-the-loop approval flows for sensitive operations.
Anthropic launches Claude Tag for Slack, writes 65% of its product team's code
Anthropic released Claude Tag, a beta feature that integrates Claude into Slack for Enterprise and Team customers. The company says the tool writes 65% of its product team's code and can work proactively with ambient mode enabled.
OpenAI releases GPT-5.5-Cyber with 85.6% CyberGym score, surpassing restricted Anthropic model
OpenAI released an updated GPT-5.5-Cyber model that scores 85.6% on CyberGym, surpassing Anthropic's Mythos 5 (83.8%) — the same model that triggered Trump administration export controls. The release proceeds without the political pushback that forced Anthropic to restrict foreign national access.
Comments
Loading...