zai-org/GLM-4.7 logo

zai-org/GLM-4.7

GLM-4.7 is Z.ai's (formerly Zhipu AI) new-generation flagship model with 355B total parameters and 32B activated per forward pass. It introduces Interleaved Thinking, Preserved Thinking, and Turn-level Thinking — enabling models to reason before actions and maintain coherent state across long coding sessions. Achieves 95.7% on AIME 2025, 73.8% on SWE-bench, and 87.4% on τ²-Bench.

Z.ai (Zhipu AI) Chat 205K Tokens
Get API Key
Try in Playground
Free Trial Credit On first TopUp of minimum $5
$1.00

api_example.sh

curl -X POST "https://platform.qubrid.com/v1/chat/completions" \
  -H "Authorization: Bearer QUBRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "zai-org/GLM-4.7",
  "messages": [
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ],
  "temperature": 0.6,
  "max_tokens": 4096,
  "stream": true,
  "top_p": 1
}'

Technical Specifications

Model Architecture & Performance

Variant FP8
Model Size 355B params (32B active)
Context Length 205K Tokens
Quantization FP8
Tokens/sec 55
Architecture Sparse Mixture-of-Experts (MoE) Transformer with 355B total / 32B active parameters
Precision FP8 (weights and KV cache)
License MIT License (commercial use allowed)
Release Date December 2025
Developers Z.ai / Zhipu AI (Tsinghua University spinoff)

Pricing

Pay-per-use, no commitments

Input Tokens $0.60/1M Tokens
Output Tokens $2.20/1M Tokens

API Reference

Complete parameter documentation

Parameter Type Default Description
stream boolean true Enable streaming responses for real-time output.
temperature number 0.6 Controls randomness. Lower values recommended for reasoning and coding.
max_tokens number 4096 Maximum number of tokens to generate.
top_p number 1 Controls nucleus sampling.
enable_thinking boolean true Enable Interleaved Thinking mode. The model thinks before every response and tool call for improved accuracy.

Explore the full request and response schema in our external API documentation

Performance

Strengths & considerations

Strengths Considerations
Interleaved Thinking for reasoning before every action
Preserved Thinking retains reasoning across coding sessions
Turn-level control over thinking per request
355B MoE with 32B active — frontier reasoning at low cost
SOTA mathematical performance (95.7% AIME 2025)
Open-source with commercial use permitted
Very large model requires significant infrastructure
FP8 inference requires natively supporting hardware
Thinking mode increases latency

Use cases

Recommended applications for this model

Agentic multilingual coding
Terminal-based task automation
Vibe coding & UI generation
Complex mathematical reasoning
Tool orchestration (Claude Code, Cline, Roo Code)
Long-horizon multi-turn tasks

Enterprise
Platform Integration

Docker

Docker Support

Official Docker images for containerized deployments

Kubernetes

Kubernetes Ready

Production-grade KBS manifests and Helm charts

SDK

SDK Libraries

Official SDKs for Python, Javascript, Go, and Java

Don't let your AI control you. Control your AI the Qubrid way!

Have questions? Want to Partner with us? Looking for larger deployments or custom fine-tuning? Let's collaborate on the right setup for your workloads.

"Qubrid's medical OCR and research parsing cut our document extraction time in half. We now have traceable pipelines and reproducible outputs that meet our compliance requirements."

Clinical AI Team

Research & Clinical Intelligence