Z.ai: GLM 5.3 Fast
by Kilo Gateway · family glm · listed Aug 2026RTW
Speed-optimized version of Z.AI’s GLM-5.3 agentic coding model, built for responsive, real-time workloads. It supports advanced coding, long-horizon task execution, testing, vulnerability discovery, and cybersecurity analysis, making it ideal for developer tools, coding agents, and complex multi-step engineering workflows.
Current rates USD per 1M tokens
Input$2.10
Output$6.60
Cache read$0.21
Cache write—
Against the market
On the record
- Model id
z-ai/glm-5.3-fast- Context window
- 1.0M tokens
- Max output
- 262K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-08-14
- Last updated
- 2026-08-14
- Provider docs
- kilo.ai
Back of the envelope
≈
Also listed at
- Wally$1.40 in · $4.40 out
- AbliteratedLLM$1.89 in · $5.94 out
- Baseten$2.10 in · $6.60 out
- Vercel AI Gateway$2.10 in · $6.60 out
- DevPass (LLM Gateway)$2.80 in · $8.80 out
- LLM Gateway$2.80 in · $8.80 out