Standard & Paid Price

The locked value is the exact Paid Price after your first top-up; the discount is derived from the two absolute prices

Unlock with a top-up

Meter	Standard Price	Paid Price	Save
Input price	$1.4000 / 1M tokens	$1.3300 / 1M tokens	-5%
Completion price	$4.4000 / 1M tokens	$4.1800 / 1M tokens	-5%
Cache read price	$0.2600 / 1M tokens	$0.2600 / 1M tokens	—

Billing details

Description

Zhipu GLM-5.3 — flagship coding-and-agent model post-trained on the same base as GLM-5.2: a 50% gain on Zhipu's internal coding bench, open-source SOTA on Terminal-Bench 3.0 and Agents' Last Exam, and state-of-the-art CyberGym vulnerability-discovery results, with a 1M-token context window and up to 128K output tokens. Text in, text out. Supports multiple thinking modes, function calling, structured JSON output, streaming, context caching, and MCP tool integration.

Capabilities

Input modalities: text
Output modalities: text
Tasks: chat, reasoning
Verified features: streaming

Decision evidence

GLM-5.3 is Z.ai's flagship open-weight mixture-of-experts model (744B total, 40B active as stated) with a 1M-token context window, 128K output tokens and text-only input; thinking is always on. Its weights come under a custom GLM-5.3 License rather than MIT, and on two independent coding leaderboards it scored 49.92 (18th of 47) on AI Coding Daily's and 52/60 on kzhu's version-2.1 test.

2026-09-25 · Markdown evidence · JSON data

API endpoints

POST /v1/chat/completions (openai)
POST /v1/messages (anthropic)