Claude Cowork logo

Run Claude Cowork on GLM-5.3-Flash

by AnthropicPersonal agent

Claude Cowork is Anthropic's agent for knowledge work — the same agentic engine as Claude Code, but built for non-technical tasks inside the Claude desktop app, with no terminal required. Give it a goal and it works across your local files, folders, and applications, planning and carrying out the task while you steer, and it's aimed at research, analysis, operations, legal, and finance teams. On Opper it runs on any of 700+ models, not just Claude: point it at Opper's Anthropic-compatible gateway and keep inference in the EU or US on one key.

RunClaude Cowork logoClaude Coworkonin

Connect Claude Cowork to GLM-5.3-Flash

Set up with agents

Claude Desktop only accepts Claude model ids, so this pairing does not run in Cowork yet. Run it in Claude Code instead →

Get your API key

Where you can run it

GLM-5.3-Flash runs on the routes below. Route only to EU providers when your data has to stay in Europe. Some routes also sell flex and priority processing: the same model at another price, picked per request with service_tier. How service tiers work.

ProviderRegionZero data retentionTrainingInputOutputCache read
EUNo$0.28$0.56Input priceNot offered on this routeNot offered on this route
EUNo$0.14$0.49$0.03Not offered on this routeNot offered on this route
EUNo$0.12$0.49$0.02Not offered on this routeNot offered on this route
EUNo$0.16$0.45$0.07Not offered on this routeNot offered on this route
EUNo$0.20$0.50$0.05Not offered on this routeNot offered on this route
EUNo$0.11$0.45$0.02Not offered on this routeNot offered on this route
EUNo$0.17$0.55$0.03Not offered on this routeNot offered on this route
EUNo$0.15$0.50$0.03
EUNo$0.20$0.60$0.07Not offered on this routeNot offered on this route
EUNo$0.20$0.50$0.05Not offered on this routeNot offered on this route
USNo$0.15$0.50$0.03Not offered on this routeNot offered on this route
USNo$0.15$0.50$0.03Not offered on this routeNot offered on this route
USNo$0.15$0.50$0.03Not offered on this routeNot offered on this route
USNo$0.11$0.40Input priceNot offered on this routeNot offered on this route
USNo$0.20$0.70$0.04Not offered on this routeNot offered on this route
USNo$0.15$0.50$0.03Not offered on this routeNot offered on this route
USNo$0.15$0.50$0.03Not offered on this route
USNo$0.10$0.35$0.02Not offered on this routeNot offered on this route
MultiNo$0.15$0.50$0.03Not offered on this routeNot offered on this route
MultiNo$0.15$0.50$0.03Not offered on this routeNot offered on this route
IndiaNo$0.14$0.45$0.03Not offered on this routeNot offered on this route
MultiNo$0.15$0.50$0.03Not offered on this routeNot offered on this route
MultiNo (opt-in)$0.45$1.50$0.09Not offered on this routeNot offered on this route
MultiNo$0.15$0.50Input priceNot offered on this routeNot offered on this route
MultiNo$0.17$0.55$0.03Not offered on this routeNot offered on this route
MultiNo$0.15$0.50$0.03Not offered on this routeNot offered on this route
MultiNo$0.15$0.50$0.03Not offered on this routeNot offered on this route
MultiNo$0.15$0.50$0.03Not offered on this routeNot offered on this route

The model

GLM-5.3-Flash by Z.ai is a natively multimodal 320B MoE with 18B active parameters, hybrid sparse and linear attention, a 1M-token context, and MIT open weights for coding and agent work.

Available on

Pricing from$0.10/ 1M input$0.35/ 1M output$0.02/ 1M cache read1.3Mcontext

Privacy

ZDR
Training
No
Region
US, EU, Multi, India

Run Claude Cowork on other models

Step-by-step setup for running Claude Cowork on each of these models through Opper.

More apps on Opper

Run Claude Cowork on GLM-5.3-Flash

One key, 700+ models, a choice of region, and zero data retention. Switch the model behind your app without changing your workflow.

Get startedView Documentation