VercelEngineering PostOfficial Source

GLM 5.3 FlashX now available on AI Gateway

GLM 5.3 FlashX brings roughly 200 tokens-per-second serving to Vercel AI Gateway, offering a lower-wait option for coding-agent output and repeated tool loops.

Vercel · Sep 18, 2026

Open Source Open Markdown Open JSON

Source Summary

Vercel AI Gateway now serves **GLM 5.3 FlashX** under `zai/glm-5.3-flashx`, with reported throughput of **about 200 tokens per second** for the multimodal coding model.

Practical Implication

For latency-sensitive agents, test it on interactive output and tool-heavy loops. Gateway setup also provides usage and cost tracking, retries, failover, budgets, and routing through one API.

Agent-Ready Context

Vercel AI Gateway now serves **GLM 5.3 FlashX** under `zai/glm-5.3-flashx`, with reported throughput of **about 200 tokens per second** for the multimodal coding model.

For latency-sensitive agents, test it on interactive output and tool-heavy loops. Gateway setup also provides usage and cost tracking, retries, failover, budgets, and routing through one API.

The material reports serving speed, not task quality, time to first token, or end-to-end tool-loop latency. Provider pricing has no gateway markup, but actual workload cost is not given.

Connected Context · Feed7 Judgment

This adds a speed-oriented multimodal coding route to the Gateway’s growing model set, with roughly 200 tokens-per-second serving throughput as a concrete screening signal. It does not resolve the prior selection problem: task quality, first-token delay, end-to-end tool-loop latency, reliability, and workload cost still require direct evaluation before default routing.

DeepSeek V4.1 Flash now available on AI GatewayBoth expand the Gateway’s multimodal coding choices, but FlashX contributes a reported throughput figure while still lacking comparative task-quality and end-to-end latency evidence.Kimi K3 and Kimi K3 Fast with ZDR and US-based providers now on AI GatewayKimi’s routes expose latency, residency, retention, and price choices; FlashX adds another speed-oriented candidate but supplies fewer operational differentiators beyond reported serving throughput.GLM 5.2 free for eve agents through August 27 via Blackbox on AI GatewayThe earlier GLM 5.2 offer lowered the cost of a bounded evaluation, whereas FlashX supplies a newer GLM route aimed at latency-sensitive use; neither provides evidence for replacing other models on task quality.

Context Map

toolscoding#coding-agents#gateways#model-selection

Uncertainty

The material reports serving speed, not task quality, time to first token, or end-to-end tool-loop latency. Provider pricing has no gateway markup, but actual workload cost is not given.