GLM 5.3

Provider: Zhipu AI (GLM) CN Official API price

Input price
$1.40
/ 1M tokens
Output price
$4.40
/ 1M tokens
Cache price
$0.26
/ 1M tokens (read)
Batch API
$0.45 / $2.00
input / output per 1M tokens
Context
1.05M tokens
Max output 131K tokens

Overview

Zhipu AI's GLM 5.3 is a reasoning model built for software engineering and long-horizon agents.

Strengths

  • 1,048,576 token context window with 131,072 max output
  • Native function calling and JSON mode support
  • Built-in thinking capabilities for complex tasks
  • Cached input drops cost down to $0.26 per million tokens

Best use cases

  • Complex software engineering workflows
  • Long-horizon autonomous agent tasks
  • Processing large codebases within 1M context

Pricing position

Priced at $1.4/1M input and $4.4/1M output, matching Qwen3.7 Max exactly.

Caveats

Output pricing exceeds DeepSeek V4 Pro peers; use Flash variants for lower costs.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
131K tokens
Listed on OpenRouter
2026-08-18
Tracked since
2026-08-19
Last updated
2026-11-10

Features

Function callingJSON outputReasoning

Price history

  • 2026-08-19 Added

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.36
1M (small app) 1 0.5 $3.60
10M (mid scale) 10 5 $36.00
100M (large) 100 50 $360.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Zhipu AI (GLM)

Similar-priced models

Source: OpenRouter API (z-ai/glm-5.3)