Models & APIs

Claude Opus 4.5 compatibility chat model

Claude Sonnet 4.5 compatibility chat model

Claude Sonnet 4.6 compatibility chat model

Use deepseek/deepseek-r1 to power AI agent reasoning and automation tasks. Ideal for complex problem-solving, code generation with Claude Code compatibility, and multi-step workflows.

Powerful chain-of-thought reasoning model, 671B parameters, 128K context, comparable to OpenAI o1 at 5-10% cost. Ideal for complex math, professional coding, scientific reasoning, and multi-step decisions.

GLM-4.7-Flash by Z.ai — 30B lightweight high-efficiency chat model. OpenAI-compatible: pass model=glm/glm-4.7-flash to /v1/chat/completions.

Qwen 3.5 Plus — Alibaba's native vision-language Plus model featuring a hybrid architecture that fuses linear attention with sparse Mixture-of-Experts, delivering superior inference efficiency. Supports multimodal inputs including text, images, and video with advanced visual understanding and deep reasoning. Demonstrates a significant performance leap over Qwen 3 in both pure-text and multimodal tasks, matching current frontier models. Built-in support for function calling, structured output, web search, prefix completion, and prompt caching.