GLM 4.7 Flash
GLM-4.7-Flash is a 30B-A3B MoE model built by Z.ai, designed for lightweight deployment balancing performance and efficiency. It demonstrates strong performance on specialized benchmarks like SWE-bench Verified and τ²-Bench.
Input
Output
Context
203K
Max Output
128K
Parameters
31.2B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Benchmarks
Estimated GPU requirements for GLM 4.7 Flash
Estimates based on INT8 quantization at up to 32K context. A count above one assumes tensor parallelism across the cards. Actual requirements vary by framework and configuration.
More models by Z.ai
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about GLM 4.7 Flash
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
GLM 4.7 Flash advertises a context window of 202,752 tokens, with a maximum output of 128,000 tokens in a single response. The figure is the creator's published maximum; a given host may serve less, and the gateway routes on what each host actually serves.
Yes. GLM 4.7 Flash is an open-weight model released under the MIT license, so the weights can be downloaded and self-hosted within that license's terms.
GLM 4.7 Flash accepts Text and produces Text. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
GLM 4.7 Flash has published results from Artificial Analysis, shown by suite in the benchmarks card above exactly as the publisher reported them. Scores are not combined across suites, and a suite that has not measured GLM 4.7 Flash is shown as not available rather than estimated.
Yes. GLM 4.7 Flash is served on the managed pool through the OpenAI-compatible endpoint as zai-glm-4-7-flash, pinned by name or chosen by routing when it is the best fit for a request. The Try in Playground button opens it directly.
About 30.7 GB at INT8 for the weights and a default context, from the catalog's 31.2B parameter count; FP16 needs roughly twice that, and long contexts or many concurrent requests add KV cache on top. The GPU section on this page lists cards that hold it, and the capacity planner sizes it for your context length and traffic.
Fields collected from public registries, host APIs and benchmark publishers, each tagged with its source.
Last updated: Sep 22, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.