Vercel AI Gateway

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...

V

Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...

V

Decider Flash V1.2 is a 4B-parameter decision model from Perplexity, a smaller, lower-cost sibling of Decider V1.2 with the same API contract. Instead of generating text, it reads content passed...

V

Decider V1.2 is a new 27B checkpoint of Perplexity's decision model, succeeding Decider V1.1 27B with the same API contract. Instead of generating text, it reads content passed as `state`...

V

Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...

VKO

d1-ultra is Liquid AI's largest decision model, served as a System One endpoint. Send a state of text and images along with typed questions, and it returns a choice, a...

V

Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...

V

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

VKNOO

Cat Jam is a reasoning model for coding and agentic workflows, combining strong coding capabilities with fast, low-latency inference. Prompts and responses may be used for training and model improvement.

V

LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...

V

Classify-1 is a structured decision model from ScaleDown, served through OpenRouter's Decisions API. It scores text or a document against caller-defined choice, yes/no, and ordered-scale questions and returns calibrated probabilities...

V

Apex is Callstack’s agentic coding model for mobile and web development, optimized for React Native, React, and Next.js. With a 256K context window, it supports feature development, debugging, code reviews, testing, and large refactors.

V

Glyph Cluster is an anonymous reasoning model in early access. Prompts and outputs may be retained by the provider.

VK

Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.

VR

MAI-Voice-2.1-Flash is a low-latency text-to-speech model from Microsoft AI, optimized for real-time responsiveness. It produces natural, expressive speech across 23 languages, with human-like intonation, rhythm, and emotional nuance. It is...

V

MAI-Voice-2.1 is Microsoft AI's highest-fidelity, most expressive text-to-speech model. It produces natural, studio-grade speech across 23 languages, with detailed prosody, nuanced expressiveness, and speaker consistency over long-form content. It is...

V

Laya is Convai Innovations’ System One evaluation model for fast, structured decisions. It evaluates shared state against choice, score, and yes/no questions and returns typed answers with probabilities in a single forward pass. It supports classification, routing, guardrail checks, and rubric-based assessment without generating free-form text.

V

MAI-Transcribe-2-Streaming is a low-latency, "speech in, text out" realtime transcription API. Audio can be sent to the model as a continuous stream over a WebSocket connection and transcripts are returned incrementally as the speaker talks, with no need to wait for the utterance to finish. Intermediate results (aka Partials) update the current transcription; final results confirm a segment.

V

rerank-3-lite is a reranker optimized for both latency and quality and a drop-in upgrade to rerank-2.5-lite, improving on it by 0.94% NDCG@10 on average across domain evaluations and by 1.86%...

V

rerank-3 is a reranker optimized for quality and a drop-in upgrade to rerank-2.5, improving on it by 0.80% NDCG@10 on average across domain evaluations and by 3.35% on long-document evaluations,...

V

Cohere's lightweight embedding model optimized for low latency and high throughput in interactive search, agent loops, and high-volume retrieval. Embed 5 Fast supports text, images, and mixed content, over 100 languages, and a 128,000-token context window, with output dimensions from 256 to 2,048. It shares an embedding space with Embed 5 Pro.

VC

Cohere's most capable embedding model for quality-critical enterprise retrieval across text, images, and mixed content such as PDFs. Embed 5 Pro supports over 100 languages and a 128,000-token context window, with output dimensions from 256 to 2,048. It shares an embedding space with Embed 5 Fast, enabling Pro indexing with Fast querying.

VC

Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers. Audio...

VG

Recraft V4.1 Flash is a text-to-image model from Recraft, the speed and cost tier of the V4.1 family. It generates ~1K raster images in about 1.5 seconds end to end,...

V

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...

VO

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...

V

SVG generation model with agentic refinement and tool calling.

V

Higher-refinement Arrow 2 variant combining Arrow's speed with frontier-model reasoning.

V

Gemini 3.8 Live is Google's model for real-time audio conversations. It supports spoken interactions for developers building voice assistants, conversational experiences, and applications that respond to users through audio.

VG

Gemini 3.8 Live Extended Thinking is Google's real-time audio model with extended thinking capabilities. It combines spoken interaction with additional reasoning for voice assistants and other conversational applications.

VG

Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...

V

Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...

V

Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...

V

Our premier model for natural, expressive voice conversations with smooth interruption handling.

V

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...

V

MAI-Image-2.6 is an image generation and editing model from Microsoft AI, the precision tier of the MAI-Image-2.6 family alongside the faster MAI-Image-2.6 Flash. It is suited for design-ready visuals and...

V

MAI-Image-2.6 Flash is the lower-latency, lower-cost member of the MAI-Image-2.6 family from Microsoft AI, built for latency-sensitive, high-throughput production image generation and editing at comparable quality to the precision tier....

V

Ling-3.0-Flash-Sante is inclusionAI’s language model specialized for health and medicine, built on a Mixture-of-Experts architecture with 124 billion total parameters and approximately 5.1 billion active per token. With a 256K context window and function calling, it supports medical knowledge reasoning, evidence-based retrieval, and complex medical workflows while retaining general reasoning, coding, and agentic capabilities.

VA

MAI-Transcribe 2 is a multilingual speech-to-text model from Microsoft AI, ranked #1 on the FLEURS multilingual benchmark. It supports 60 languages with automatic language identification, code switching for mixed-language speech,...

V

Fetch the contents of a URL with Browserbase, optionally through proxies, returning the upstream response body unchanged or content extracted as Markdown or JSON. Use it as a built-in tool through the AI Gateway to let any model read a page it already has a URL for.

V