Guide

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,...

Vercel AI Gateway is a single API for hundreds of models from OpenAI, Anthropic, Google, xAI, Meta, Mistral, DeepSeek, and more. One API key and one bill cover every provider. It adds automatic retries and fallbacks across providers, budgets and spend tracking, request logs, and bring-your-own-key support, all behind an OpenAI-compatible endpoint that works with any OpenAI-compatible client.

Meta Model API is Meta's developer platform for its Muse Spark models. Muse Spark accepts text, images, PDFs, video, and audio as input, making it a good fit for multimodal chat and document analysis. The API uses pay-as-you-go pricing and is drop-in compatible with the OpenAI SDK, so it works with any OpenAI-compatible client. The same console includes chat and image playgrounds, usage tracking, and billing.

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

MiMo pro model for strong multimodal reasoning and agent execution

MiMo pro model for strong multimodal reasoning and agent execution

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...

GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...

Flagship Claude model for deep reasoning, coding, and long-horizon agents

High-speed GLM-5.3-Flash serving option for coding and agent workflows

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

Qwen omni model for text, vision, audio, and multimodal agent tasks

Qwen omni model for text, vision, audio, and multimodal agent tasks

Blended multimodal model that runs multiple language models in parallel and returns a synthesized answer

Grok model for agentic tool use, reasoning, coding, and live assistance

Fast SVG generation model for creation, vectorization, editing, and animation

High-fidelity SVG generation model for complex vector work and long-context refinement

StepFun flash model for efficient multimodal reasoning, coding, and tool use

Speech generation model for controllable voice, narration, and audio delivery

Speech generation model for controllable voice, narration, and audio delivery

This model always redirects to the latest model in the DeepSeek Pro family.

This model always redirects to the latest model in the DeepSeek Flash family.

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...

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...

This model always redirects to the latest model in the GPT Astra family.

This model always redirects to the latest model in the GPT Sol family.

This model always redirects to the latest model in the GPT Terra family.

This model always redirects to the latest model in the GPT Luna family.

Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...

Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...

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...

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

DeepSeek V4.1 Flash model for reasoning and agentic coding

DeepSeek V4.1 Flash model for reasoning and agentic coding

DeepSeek V4.1 Flash model for reasoning and agentic coding

DeepSeek V4.1 Flash model for reasoning and agentic coding

DeepSeek V4.1 Flash model for reasoning and agentic coding

Qwen vision-language model for visual reasoning, documents, and agent tasks

Fast DeepSeek model for efficient chat, coding help, and agent loops

DeepSeek V4.1 Flash model for reasoning and agentic coding

DeepSeek V4.1 Flash model for reasoning and agentic coding

Fast DeepSeek model for efficient chat, coding help, and agent loops

DeepSeek V4.1 Flash model for reasoning and agentic coding

DeepSeek V4.1 Flash model for reasoning and agentic coding

Multi-agent model for routing expert agents across complex analytical tasks