TheRouter.aiTheRouter.ai

Provider profile: Zhipu — Zhipu AI builds the GLM model family from Tsinghua spin-off research. TheRouter routes directly to BigModel (open.bigmodel.cn) for the full GLM-4.7 / 4.6V / OCR / image-gen / video-gen / embeddings lineup, avoiding aggregator markup. Coverage spans chat (GLM-4.7 Sonnet-tier reasoning, GLM-4.6V native function-calling vision, GLM-OCR document parsing), image generation (GLM-Image, CogView 4), video generation (CogVideoX 3, Vidu Q1 and Vidu 2 families), embeddings (Embedding 3 / 2), plus a free tier on cogview-3-flash, cogvideox-flash, glm-4.7-flash, glm-4.6v-flash, and glm-4.1v-thinking-flash.

← All providers

Zhipu

China29 models

GLM series — China-direct supply with vision, OCR, image, video, and embeddings

Zhipu AI builds the GLM model family from Tsinghua spin-off research. TheRouter routes directly to BigModel (open.bigmodel.cn) for the full GLM-4.7 / 4.6V / OCR / image-gen / video-gen / embeddings lineup, avoiding aggregator markup. Coverage spans chat (GLM-4.7 Sonnet-tier reasoning, GLM-4.6V native function-calling vision, GLM-OCR document parsing), image generation (GLM-Image, CogView 4), video generation (CogVideoX 3, Vidu Q1 and Vidu 2 families), embeddings (Embedding 3 / 2), plus a free tier on cogview-3-flash, cogvideox-flash, glm-4.7-flash, glm-4.6v-flash, and glm-4.1v-thinking-flash.

  • ✓Vision
  • ✓OCR
  • ✓Reasoning
  • ✓Image generation
  • ✓Video generation
  • ✓Embeddings
  • ✓Function Call
  • ✓Prompt Caching
VisionOCRReasoningImage generationVideo generationEmbeddingsFunction CallPrompt Caching

Models

CogVideoX 3Zhipu AI CogVideoX 3 — flagship text/image-to-video generation. Up to 5s or 10s, up to 4K resolution.CogVideoX FlashZhipu AI CogVideoX Flash — free-tier text/image-to-video generation.CogView 3 FlashZhipu AI CogView 3 Flash — free-tier text-to-image generation for trial and low-volume use.CogView 4Zhipu AI CogView 4 — text-to-image generation with strong bilingual prompt understanding.Embedding 2Zhipu AI Embedding 2 — text embedding model with fixed 1024-dim output.Embedding 3Zhipu AI Embedding 3 — latest text embedding model. Default 2048-dim, supports custom dimensions (256, 512, 1024, 2048).GLM 4.1V Thinking FlashZhipu AI GLM 4.1V Thinking Flash — free-tier always-on chain-of-thought vision model supporting image and video inputs.GLM 4.1V Thinking FlashXZhipu AI GLM 4.1V Thinking FlashX — always-on chain-of-thought vision model supporting image and video inputs for complex visual reasoning.
Browse all models →
Customer Support