Z.ai / Zhipu AIWeights not listed·1000K context·320B params
GLM 5.3 FlashXzhipu/glm-5-3-flashx
GLM 5.3 FlashX is a multimodal reasoning model for visual analysis, software development and agent tasks. The Flash architecture has 320B total parameters with 18B active per token; FlashX is the faster hosted serving option. Both accept visual inputs and generate text.
Availability and billing notes
Reviewed September 21, 2026 · check the linked provider documentation for later changes.
Reasoning is always enabled. The advertised serving speed is a vendor claim, not an independently measured latency result.
Prices below are USD rates from the international Z.ai API. Coding Plan allowances and mainland China pricing are separate.
Pricing across providers
No current verified API pricing is listed. See the official model documentation for availability and billing.
Capabilities
- reasoning
- code
- vision
- tool_calling
Technical specs
- Context
- 1000K
- Max output
- —
- Parameters
- 320B
- Release
- —
- Training cutoff
- —
- License
- —
Similar models
Compare with
- GLM 5.3 FlashX vs GLM 5.3 FlashComparison planned — not yet published
- GLM 5.3 FlashX vs Qwen3.5 397B A17BComparison planned — not yet published
- GLM 5.3 FlashX vs Step 3.7 FlashComparison planned — not yet published
Frequently asked
How much does GLM 5.3 FlashX cost?+−
No current verified API pricing is listed. This does not mean the model is free or that a hosted API is currently available. Check the official model documentation below.
How do I access GLM 5.3 FlashX from outside China?+−
Availability, account verification and payment methods vary by provider and region. Check the official documentation and the selected provider's access requirements before integrating. A directory listing does not guarantee global API access.
Is GLM 5.3 FlashX open-source?+−
Downloadable weights are not listed in this directory for GLM 5.3 FlashX. See the official documentation and availability notes for API, subscription or planned weight-release details.
What's the maximum context window for GLM 5.3 FlashX?+−
The model supports up to 1,000,000 tokens of context (input + output). Some hosted versions may impose a smaller limit — check the "Context" column in the pricing matrix for each provider.