Cat Jam is now available in stealth for free on AI Gateway
Quick Answer
Cat Jam, a new reasoning model for coding tasks, is now available for free on AI Gateway during its stealth phase.
Quick Take
It supports and structured JSON outputs, but lacks Zero Data Retention. Users can integrate it with various coding agents and utilize the Vercel CLI for setup.
Key Points
- Cat Jam offers low-latency inference for coding and agentic tasks.
- It supports function calling and structured outputs based on user-defined JSON schemas.
- Zero Data Retention (ZDR) is not available; prompts may be retained for safety.
- Compatible with AI SDK and various APIs, including OpenAI and Anthropic.
- No platform fees on inference, reflecting provider pricing directly.
DeepSignal Analysis
What happened
Cat Jam, a reasoning model for coding tasks, has been launched on AI Gateway as a free-to-use stealth model. It supports function calling and structured JSON outputs but does not offer Zero Data Retention, meaning prompts may be retained for safety reasons.
Key evidence
- Cat Jam is available for free during its stealth phase on AI Gateway, focusing on coding and agentic tasks.
- The model supports function calling and structured outputs that adhere to a JSON schema provided by the user.
- Zero Data Retention is not available for Cat Jam, indicating that prompts may be stored for safety purposes.
Why it matters
The introduction of Cat Jam could enhance the capabilities of coding agents by providing a reasoning model that supports various levels of reasoning effort. However, the lack of Zero Data Retention may raise concerns regarding user privacy and data security, which are critical in AI applications.
What to watch
Monitor how users respond to the lack of Zero Data Retention and whether this affects adoption rates. Additionally, observe any updates or changes in the model's capabilities or privacy policies as it moves beyond the stealth phase.
📖 Reader Mode
~2 min readCat Jam is now available on AI Gateway as a stealth model, free to use during the stealth period.
Cat Jam is a reasoning model for coding and agentic tasks, with low-latency inference. It supports function calling, so agents can connect it to your own tools, and structured outputs that follow a JSON schema you supply. Responses include the model's reasoning text alongside the answer. Cat Jam takes text input only. Cat Jam supports low, medium, high, xhigh, and max reasoning efforts.
Zero Data Retention (ZDR) is not available for this model. Prompts may be retained for safety reasons.
Cat Jam works with the AI SDK, the OpenAI-compatible Chat Completions and Responses APIs, the Anthropic-compatible Messages API, and coding agents connected to AI Gateway. Use stealth/cat-jam as the model name:
To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup:
npx vercel ai-gateway setup
Then select stealth/cat-jam in the agent. See the coding agents guide for details.
Try Cat Jam in the model playground.
AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, budgets for API keys, routing rules, and more.
AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests.
You can view all language models available on AI Gateway.
— Originally published at vercel.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from Vercel AI
See more →
The Agent Stack
The Agent Stack by Vercel AI provides essential building blocks for creating production-grade agents, enabling seamless integration across multiple AI models and secure operations. It features components like AI Gateway for model routing, Workflow SDK for durable execution, and Vercel Connect for scoped access, streamlining agent development and deployment across various platforms.
