GLM-5.3
Always reasons1.3M contextFlagship Z.ai mixture-of-experts for coding and long-horizon agent work
Open model access
Open models for asynchronous agents and workflows. Compare Realtime, Async and Batch token rates, with cost per completed job in view.
https://api.qloud.sh/v1client = OpenAI(
base_url="https://api.qloud.sh/v1",
api_key=QLOUD_API_KEY,
)
client.chat.completions.create(
model="DeepSeek-V4-Flash-0731",
messages=messages,
)OpenAI-compatible chat completions. Async and Batch on the same models.
Batch leads on price when work can wait.
Batch inference
$1.20per completed job
$2.80 saved vs Realtime · 70% lower
For latency-tolerant agents and workflows with room to wait.
Per 1M tokens, GLM-5.3 list rates.
Batch: $1.20 per completed job.
Models are added as they ship. Quantized variants are labelled, never swapped in silently for the checkpoint you asked for.
Always reasons1.3M contextFlagship Z.ai mixture-of-experts for coding and long-horizon agent work
Always reasons1.3M contextThe fast GLM-5.3 tier, for high-volume agents and interactive work
Reasoning1M contextFrontier open reasoning and tool calling for hard, low-volume work
Low latency1.3M contextThe GA revision of V4 Flash: sparse MoE for coding, reasoning and agents
Low latency1M contextThe V4.1 Flash line: a newer revision than 0731, at a higher rate
Always reasons1M contextMeta's open-weight coding model, tuned for agentic workflows and tool calling