Get started

GLM 5.3 Flash

Retiring November 1, 2026

Open weights by Z.ai

The model behind umans-coder today: a strong all-rounder for everyday coding that also reads images, at a flash price. It retires on November 1, 2026. umans-coder moves to DeepSeek V4.1 Flash before then; if you call this model by name, switch to DeepSeek V4.1 Flash.

Get an API keyLive status
Price per 1M tokens
$0.15 in$0.50 out
$0.03 cache read
Context
1M
128K max output
Parameters
320B
18B active
Weights
FP8
Official release
  • Vision
  • Tool calling
  • Reasoning always on, default max

How it ranks

Against every model we serve, best first. Starred scores are reported by the publisher on its model card; the rest are independent measurements. About the scores

Artificial Analysis Intelligence Indexby Artificial Analysis
  1. DeepSeek V4.1 Flash45
  2. GLM 5.345
  3. Kimi K344
  4. GLM 5.3 Flash42
  5. DeepSeek V4 Flash34
  6. Qwen3.6 35B A3B18
DeepSWEby Datacurve
  1. DeepSeek V4.1 Flash77%* reported by the publisher
  2. GLM 5.369%
  3. Kimi K368.5%
  4. GLM 5.3 Flash63.4%
  5. DeepSeek V4 Flash54.4%* reported by the publisher

Not published: Qwen3.6 35B A3B.

Terminal-Bench 2.1by tbench.ai
  1. DeepSeek V4.1 Flash90.6%* reported by the publisher† measured before the 1017 update
  2. Kimi K385%
  3. GLM 5.3 Flash84.3%
  4. GLM 5.383.9%
  5. DeepSeek V4 Flash78.7%
  6. Qwen3.6 35B A3B44.9%

† DeepSeek V4.1 Flash: measured on its previous weights, before the 1017 update. No 2.1 score yet for 1017; on Terminal-Bench 4.0 the update took it from 26.8% to 33.8% (Artificial Analysis).

  • Artificial Analysis Intelligence Index for GLM 5.3 Flash: independent measurement. Source
  • DeepSWE for GLM 5.3 Flash: independent measurement. Source
  • Terminal-Bench 2.1 for GLM 5.3 Flash: independent measurement. Source

Pricing

Input
$0.15 per 1M tokens
Output
$0.50 per 1M tokens
Cache read
$0.03 per 1M tokens

See all prices

Specs

Context window
1M tokens
Max output
128K tokens
Parameters
320B total, 18B active per token
Vision
Yes
Tool calling
Yes
Reasoning
Always on (low, high, max)
Default effort
max
Weights
FP8, official release
In production since
September 9, 2026

Quickstart

Pick your tool; the command already carries this model's id. More tools (Pi, Copilot, Zed, omp) in the setup guides.

OpenCode
Built in
Launch OpenCode on this model with the umans CLI. Umans AI is also built into OpenCode: run /connect and pick it.
Terminal
curl -fsSL https://api.code.umans.ai/cli/install.sh | bash   # once
umans opencode --model umans-glm-5.3-flash
Full setup in the docs

Or consider

GLM 5.3 Flash API: pricing, context and benchmarks · Umans AI