by Z.ai·Text·200K context·Released 2026-01-28·MIT
Overview
Z.ai's open-weight GLM-5, a large model tuned for agentic coding and tool use that has become popular as a low-cost backbone for autonomous coding agents. Strong real-world coding performance for the price, hosted by several providers under a permissive license. A good open alternative to the pricier hosted agent models.
Benchmarks
Standardized scores (0–100), normalized across the catalog.
Intelligence83
Coding87
Instruction following89
Providers
LLMRouteHub routes to the cheapest healthy provider by default.
| Provider | Input | Output | Throughput | Uptime |
|---|---|---|---|---|
| Groq | $0.62 | $2.30 | 86 tok/s | 99.5% |
| Lambda | $0.76 | $2.80 | 80 tok/s | 99.4% |
| Hyperbolic | $0.80 | $2.98 | 74 tok/s | 99.2% |
| Parasail | $0.94 | $3.48 | 68 tok/s | 99.1% |
| DeepInfra | $1.07 | $3.99 | 62 tok/s | 98.9% |
Use this model
curl https://llmroutehub.com/api/v1/chat/completions \
-H "Authorization: Bearer $LLMROUTEHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "z-ai/glm-5",
"messages": [{ "role": "user", "content": "Hello" }]
}'