GLM-4.7 is a Zhipu/Z.ai model family; the sources do not name GLM-4.7 directly. Z.ai's own page features GLM-5.3-Flash 4, and GLM models are available through OpenRouter 3 and AINative Studio, which offers GLM-4.6 among its models 5. Replicate hosts a GLM vision model, GLM-4V-9B, which is a different model 16.
- 1
Z.aiz.aiverified and signed
Z.ai is the chatbot and agent from the GLM model maker, powered by GLM-5.3-Flash, and its Zhipu action covers building AI applications with GLM models 9.
for agents: zhipu
- 2
OpenRouteropenrouter.aiverified and signed
OpenRouter is a unified API that routes requests to hundreds of models from many providers, with tool calling and structured outputs available on its models 8.
for agents: tool-calling · structured-outputs · text->text
- 3
AINative Studioainative.studiowebsite read, tools not yet checked
AINative Studio offers GLM models such as GLM-4.6 on one OpenAI-compatible API, paid after a 3-day trial.
- 4
Replicatereplicate.comverified and signed
Replicate runs open-source models through a cloud API, including cuuupid/glm-4v-9b, a GLM-4V multimodal model from Tsinghua University 6; this is a different model from GLM-4.7.
for agents: cuuupid/glm-4v-9b
Sources
- 1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 3OpenRouteropenrouter.ai · read 2026-10-29
- 4Z.ai - Advanced AI Chatbot & Agent powered by GLM-5.3-Flashchat.z.ai · read 2026-10-29
- 5AINative Studio | Frontier Open Models (Kimi K3, GLM, DeepSeek) — Best Price, One APIainative.studio · read 2026-10-29
- 6cuuupid/glm-4v-9b: declares "cuuupid/glm-4v-9b" (the record we read and signed)unfragile.ai · read 2026-10-24
- 8Z.ai: GLM 4.7: declares "tool-calling" (the record we read and signed)unfragile.ai · read 2026-10-24
- 9Overview - Z.AI DEVELOPER DOCUMENT: declares "zhipu" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
cuuupid/glm-4v-9b · cuuupid/glm-4v-9b verified and signed
GLM-4V is a multimodal model released by Tsinghua University that is competitive with GPT-4o and establishes a new SOTA on several benchmarks, including OCR.
anthropic/claude-opus-4.7 · anthropic/claude-opus-4.7 verified and signed
Anthropic's most capable model with a step-change improvement in agentic coding, better vision, and stronger multi-step reasoning
typespec-api-operations · typespec-api-operations verified and signed
Add GET, POST, PATCH, and DELETE operations to a TypeSpec API plugin with proper routing, parameters, and adaptive cards
tool-calling · Z.ai: GLM 4.7 verified and signed
Can call tools (function calling).
lucataco/glm-ocr · lucataco/glm-ocr verified and signed
Compact 0.9B multimodal OCR model from Z.ai. State-of-the-art on OmniDocBench V1.5 (94.62, #1 overall). Four modes: text recognition, formula (LaTeX), table parsing, and JSON-schema information extraction. Fits on a single T4.
bytedance/sdxl-lightning-4step · bytedance/sdxl-lightning-4step verified and signed
SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps
meta/llama-4-maverick-instruct · meta/llama-4-maverick-instruct verified and signed
A 17 billion parameter model with 128 experts
openai/gpt-4o-transcribe · openai/gpt-4o-transcribe verified and signed
A speech-to-text model that uses GPT-4o to transcribe audio
cjwbw/cogvlm · cjwbw/cogvlm verified and signed
powerful open-source visual language model
beautyyuyanli/multilingual-e5-large · beautyyuyanli/multilingual-e5-large verified and signed
multilingual-e5-large: A multi-language text embedding model
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.