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
xAI's Grok 4.6 Launches on Amazon Bedrock With 500K Context and Cross-Region Inference
xAI's Grok 4.6 is now available on Amazon Bedrock via both bedrock-mantle and bedrock-runtime endpoints, adding Converse API support, cross-Region inference profiles, and Bedrock Guardrails. The model offers a 500K token context window and four reasoning effort levels, with input pricing starting at $2.00 per million tokens on the global inference profile.
Claude Code 2.1.277 Adds AGENTS.md Support Via New Mods System
Anthropic engineer Thariq Shihipar announced that Claude Code version 2.1.277 now supports AGENTS.md files as a fallback when no CLAUDE.md is present. The feature is implemented through Claude Code mods, a new customization system for the coding agent's harness.
Anthropic Builds Physical Biology Lab Where Claude Directs Robots to Run Drug Experiments
Anthropic is setting up a physical biology lab in the San Francisco area where Claude will guide robots through drug experiments with minimal human involvement. The move follows the company's $400 million acquisition of Coefficient Bio and the addition of Novartis CEO Vas Narasimhan to its board.
Meta's Muse AI Agent App Hits 730,000 Downloads, Overtakes ChatGPT on iOS Charts
Meta's Muse AI agent app overtook ChatGPT as the top free iOS app in the U.S., racking up 730,000 downloads in its first five days, according to Sensor Tower. The app, powered by Meta's Muse Spark model family, marks Zuckerberg's biggest push yet into AI agents.
Comments
Loading...