Coding GLM 5.3

coding-glm-5.3 · Z.AI

GLM-5.3 is Z.ai’s reasoning model for coding and agentic workflows, designed for complex software engineering, long-running agents, and vulnerability analysis. It uses the same base model as GLM-5.2, with scaled post-training improving coding, task execution, and token efficiency. This model is a limited-time preview version of GLM-5.3, intended for testing and evaluation only. Service stability is not guaranteed, and we do not recommend using it in production environments. We’re waiting for the official commercial API release and will integrate it as soon as official support becomes available.

API Pricing

Input$0.06 / 1M tokens
Output$0.22 / 1M tokens
Cache read$0.015 / 1M tokens

Specifications

Context1.05M tokens
Max output131K tokens
Modalitiestext
CapabilitiesThinking, Streaming, Tool calling, Structured outputs, Prompt caching
Endpointschat_completions, claude_api

Frequently asked questions

What is GLM 5.3 (coding)?

GLM-5.3 is Z.ai’s reasoning model for coding and agentic workflows, designed for complex software engineering, long-running agents, and vulnerability analysis. It uses the same base model as GLM-5.2, with scaled post-training improving coding, task execution, and token efficiency. This model is a limited-time preview version of GLM-5.3, intended for testing and evaluation only. Service stability is not guaranteed, and we do not recommend using it in production environments. We’re waiting for the official commercial API release and will integrate it as soon as official support becomes available.

What is the context length of GLM 5.3 (coding)?

GLM 5.3 (coding) has a 1,048,576 token context window. It supports up to 131,072 output tokens.

How much does GLM 5.3 (coding) cost?

On AIHubMix, GLM 5.3 (coding) costs $0.06 per million input tokens and $0.22 per million output tokens. Cached input reads are billed at $0.015 per million tokens.

What modalities does GLM 5.3 (coding) support?

GLM 5.3 (coding) accepts text input.

What capabilities does GLM 5.3 (coding) support?

GLM 5.3 (coding) supports thinking, tool calling, function calling and structured outputs. Per-protocol parameter support is listed in the capability table on this page.

How do I call GLM 5.3 (coding) via API?

GLM 5.3 (coding) is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to coding-glm-5.3 — no other code changes needed.

Who created GLM 5.3 (coding)?

GLM 5.3 (coding) is developed by Z.AI. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

When was GLM 5.3 (coding) released?

GLM 5.3 (coding) was released on August 14, 2026 by Z.AI.

Free version: Coding GLM 5.3 (free)

More models from Z.AI

See all Z.AI models →

GLM 5.3 Flash

by Z.AI

GLM-5.3-Flash is a high-efficiency multimodal model from Z.AI. It supports a context…

$0.113 $0.056/1M in · $0.394 $0.197/1M out
50% off
1,000,000 tokens context

GLM 5.3

by Z.AI

GLM-5.3 is Z.AI’s coding and agentic reasoning model, built for complex software…

$1.127 $1.014/1M in · $3.944 $3.549/1M out
10% off
1,000,000 tokens context

Coding GLM 5.3 Flash (free)

by Z.AI

coding-glm-5.3-flash-free is the open and free version of coding-glm-5.3-flash. To ensure…

Coding GLM 5.3 Flash

by Z.AI

Coding GLM 5.3 Flash is a dedicated version of GLM 5.3 Flash built for AI coding and…

$0.028/1M in · $0.099/1M out
1,000,000 tokens context

Coding GLM 5.3 (free)

by Z.AI

coding-glm-5.3-free is the open and free version of coding-glm-5.3. To ensure stable…

Ox Alpha

by Z.AI

This model actually points to glm-5.3-flash; if you need to use it in production, you can…

1,048,576 tokens context

Use Coding GLM 5.3 via the AIHubMix unified API — one interface for every major LLM.