GLM-4.5
by Abacus · family glm · listed Jul 2025RTW
Hybrid-reasoning GLM release that made the 4.5 line broadly useful
Current rates USD per 1M tokens
Input$0.60
Output$2.20
Cache read—
Cache write—
Against the market
On the record
- Model id
zai-org/GLM-4.5- Context window
- 131K tokens
- Max output
- 96K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Apr 2025
- Released
- 2025-07-28
- Last updated
- 2025-07-28
- Provider docs
- abacus.ai/help/api
Back of the envelope
≈
Also listed at
- ModelScopefree in · free out
- 302.AI$0.286 in · $1.14 out
- NanoGPT$0.30 in · $1.30 out
- ZenMux$0.35 in · $1.54 out
- Zhipu AI$0.60 in · $2.20 out
- Impossibl$0.60 in · $2.20 out
- LLM Gateway$0.60 in · $2.20 out
- OrcaRouter$0.60 in · $2.20 out
- Kilo Gateway$0.60 in · $2.20 out
- Merge Gateway$0.60 in · $2.20 out
- Vercel AI Gateway$0.60 in · $2.20 out
- NovitaAI$0.60 in · $2.20 out
- OpenRouter$0.60 in · $2.20 out
- Hugging Face$0.60 in · $2.20 out
- Jiekou.AI$0.60 in · $2.20 out