VercelVercel's AI Gateway picked up two new models this week, one for reasoning and multimodal tasks, one for image generation. Both arrive with a single API key through the same gateway, so there's no separate account to set up before you can call them.
Mistral Large 4
Mistral Large 4 is now available on AI Gateway. It's an open-weight, natively multimodal model that combines reasoning with text and image understanding, and it works through the AI SDK, the OpenAI-compatible Chat Completions API, the Responses API, or the Anthropic Messages API. You can also pick it directly inside coding agents connected to AI Gateway, with Vercel pointing to cyber defence, manufacturing, and finance as fit use cases.
Nano Banana 2.1
Nano Banana 2.1 is Google's latest image generation model, now live on AI Gateway under the model ID google/gemini-nano-banana-2.1. It improves on earlier versions with better product recontextualisation and mask- and ink-based editing, and it produces photorealistic skin tones, materials, lighting, and backgrounds at Flash-tier speed and cost. Call it through the AI SDK, the Chat Completions API, or the AI CLI, with generated images coming back in result.files.
Both additions follow Vercel's recent run of AI Gateway updates, including confidence-based decision fallbacks and Browserbase search and fetch, which keep widening what you can route through one gateway without juggling separate provider accounts.
Sources
2 checkedHow we cover tool news: Create With's tool desk drafts these reports with AI from the sources listed above and checks them against those sources before publishing.
ElevenLabs
Notion
