GLM 5.3 Flash (batch)

Z.ai· released 26 Aug 2026

z-ai/glm-5.3-flash:batch
Input / 1M tokens
$0.06
Output / 1M tokens
$0.2
Context window1M tokens

Longest answer: 131K tokens

reads textreads imagereads videoopen weightstool callingvisionreasoning

About

GLM 5.3 Flash (batch) is Z.ai’s open-weight native multimodal model, suited to efficient coding and long-horizon agent tasks. It accepts text, image, and video inputs and produces text, with tools and reasoning supported. Its context window is 1,048,576 tokens and its maximum output is 131,072 tokens. The model was released on 2026-08-26. Input costs 0.06 USD per 1M tokens, and output costs 0.2 USD per 1M tokens. For builders, its multimodal inputs and tool support are relevant to coding and agent workflows that may use long contexts. Open weights are listed, along with the Hugging Face identifier zai-org/GLM-5.3-Flash. The batch model identifier is z-ai/glm-5.3-flash:batch.

Who it is for

It suits teams working on coding or long-horizon agent tasks that need text, image, or video input. Open weights and tool support may matter when assessing stack fit.

What is good

  • Open weights are available.
  • Accepts text, image, and video inputs.
  • Supports tools and reasoning.
  • Context window is 1,048,576 tokens.
  • Input costs 0.06 USD per 1M tokens.

What to know first

  • Output costs 0.2 USD per 1M tokens.

Verdict

GLM 5.3 Flash (batch) pairs multimodal input and tool use with a million-token context window. Its listed coding and agent focus and per-token prices help frame an evaluation.

Details

Lab
Z.aiopenrouter.ai · 3 Oct 2026
Context
1,049Kopenrouter.ai · 3 Oct 2026
Input price
$0.06 / 1Mopenrouter.ai · 3 Oct 2026
Output price
$0.2 / 1Mopenrouter.ai · 3 Oct 2026
Max output
131,072 tokensopenrouter.ai · 3 Oct 2026
Inputs
text, image, videoopenrouter.ai · 3 Oct 2026
Open weights
Yesopenrouter.ai · 3 Oct 2026

More newest models

See the list