Models
glm-5.2 — API, Pricing & Context Window | Vivgrid
glm-5.2 on Vivgrid: Zhipu AI's coding model with a 1M-token context window, function calling, and competitive pricing.
glm-5.2 is Zhipu AI's latest coding and reasoning model, pairing reliable function calling with a major upgrade: a 1M-token context window, up from 200K in glm-5.1. It's a strong, low-cost option for agentic coding workloads that need to reason over large codebases.
On Vivgrid, glm-5.2 is reachable through the unified, OpenAI-compatible endpoint, so it integrates cleanly alongside models from OpenAI, Anthropic, Google, and DeepSeek under one API key.
Specifications
| Provider | Zhipu AI |
| Model ID | glm-5.2 |
| Best for | Coding |
| Context window | 1,000,000 tokens |
| Max output | 128,000 tokens |
| Modalities | Text |
| Tool / function calling | Yes |
| Knowledge cutoff | 2026-06 |
| Acceleration | 🌐 Global (Centralized) |
Pricing
Pricing in USD per 1M tokens, matching the provider's rates.
| Input | Cached input | Output |
|---|---|---|
| $1.20 | $0.30 | $4.20 |
Quick start
Call glm-5.2 through Vivgrid's unified, OpenAI-compatible endpoint. Get an API key from the Vivgrid Console.
curl https://api.vivgrid.com/v1/chat/completions \
-H "Authorization: Bearer $VIVGRID_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.2",
"messages": [
{ "role": "user", "content": "Say hello in English, Chinese and Spanish." }
],
"stream": true
}'Ideal use cases
- Cost-effective coding agents and CLIs
- Whole-repository reasoning within a 1M-token context
- Tool-calling workflows on Chat Completions
- Teams diversifying beyond US-based providers
Related models
- glm-5.1 — prior-generation model with a 200K context
- deepseek-v4-pro — flagship low-cost coding model
- kimi-k2.6 — alternative high-context coding model