Router DeskHomeGLM 5.2 API
GLM 5.2 API
Z.ai’s GLM 5.2 is a long-context reasoning model. On OpenRouter the id is z-ai/glm-5.2.
Updated 2026-09-27
OpenRouter describes GLM 5.2 as a large reasoning model for long agent runs and project-scale coding, with text in and text out. The models API on 27 Sep 2026 listed a 1,048,576-token context, $0.650 per million input tokens, $2.042 per million output tokens, and cache reads at about $0.121 per million.
{
"model": "z-ai/glm-5.2",
"messages": [{ "role": "user", "content": "Plan the migration, then list the files." }]
}Newer GLM 5.3 cards were already on the catalog the same day, at different prices. glm-5.2 is the id this search is about. If a changelog says “latest GLM,” read the slug before you copy a price into a budget.
Put beside DeepSeek V4 Pro 0423 ($0.348 / $0.696) and Qwen3.7 Max ($1.475 / $4.425), GLM 5.2 sits in the middle on input and near the top of this open-weight set on output. A coding agent that writes a lot of tokens will feel the $2.04 output rate.
Questions
How much is GLM 5.2 on OpenRouter?
$0.650 per million input tokens and $2.042 per million output tokens on 27 Sep 2026.
What is the model id?
z-ai/glm-5.2
Does GLM 5.2 have a million-token context?
Yes. The models API listed 1,048,576 tokens.
Related
- Coding models
Coding-model choice on OpenRouter is price, context, and tool-call reliability. DeepSeek V4, Qwen3.7 Max, GLM 5.2, and Sonnet 5 are the slugs to price first.
- Qwen3 Max
Qwen3.7 Max was $1.475 input and $4.425 output per million tokens on 27 Sep 2026, with a 1M context. The older qwen/qwen3-max slug was $0.78 / $3.90.
- DeepSeek API price
On 27 Sep 2026 OpenRouter listed DeepSeek V4 Pro 0423 at $0.348 / $0.696 per million tokens, and V4 Pro 0813 at $0.245 / $3.50.
- AI model comparison
A price and context comparison of DeepSeek V4, Qwen3.7 Max, GLM 5.2, Claude Sonnet 5, GPT-5.1, and Grok 4.5 on OpenRouter, checked 27 Sep 2026.