AI Inference

x402engine — OpenAI's SOTA agentic coding model — best-in-class for software engineering and code generation

x402engine — OpenAI's code-specialized reasoning model — optimized for software engineering tasks

x402engine — Anthropic's balanced frontier model with 1M context and strong coding performance

x402engine — xAI's latest multimodal model with 500k context and strong tool use

x402engine — OpenAI's cheapest GPT-5 tier — ultra-affordable for high-volume agent tasks

x402engine — Meta's open-source model — great general-purpose performance at very low cost

x402engine — Tencent's efficient reasoning model with a 262k-token context window

x402engine — GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention…

x402engine — Fast, affordable GPT-4o variant — great for simple tasks and high-volume use

x402engine — Alibaba's code-specialized model — optimized for code generation, review, and technical tasks

x402engine — Meta's latest open model — 1M context, strong multilingual and reasoning at very low cost

x402engine — DeepSeek's latest flagship model — improved reasoning and coding over V3 at same low cost

x402engine — DeepSeek V3.2 served on the Speciale compatibility route — strong reasoning and coding at low cost

x402engine — Alibaba's flagship open model — excellent multilingual and coding capabilities

x402engine — MiniMax's efficient model — fast and affordable for everyday tasks

x402engine — MiniMax's multimodal foundation model — 1M context for agentic work, coding, and long-document tasks

x402engine — MiniMax's latest model — improved reasoning and generation with 204k context

x402engine — Meituan's long-context model for reasoning, coding, and high-volume inference

x402engine — Alibaba's latest model — 1M context, strong multilingual and coding capabilities

x402engine — Google's fastest and cheapest model — ideal for high-volume, low-latency tasks

x402engine — Mistral's code-focused model — optimized for software development and technical tasks

x402engine — Google's low-cost multimodal model for high-volume agent workloads

x402engine — OpenAI's efficient GPT-5.6 tier with a 1M-token context window

x402engine — OpenAI's higher-compute Luna tier for efficient long-context reasoning