GLM 5.2 FP8
Recommended for long-document Q&A, code, and agentic workloads that need a 1M-token context window.
zai-org/GLM-5.2-FP8
About
GLM 5.2 FP8 is Z.AI’s GLM-series generalist, served in FP8 with a 1,048,576-token context window. It is the successor to GLM 5.1 FP8 on the Corvex platform and is a strong default for long-context chat, code, and instruction-following workloads.Pricing
| Direction | Rate (USD) |
|---|---|
| Input | $0.50 / 1M tokens |
| Output | $2.00 / 1M tokens |
Capabilities
chatreasoningcoding
Specs
- Context window: 1,048,576 tokens (1M)
- License: MIT
Recommended use cases
- Chat and instruction following
- Tool use and function calling
- Long-document Q&A and summarization
Benchmarks
Benchmarks fill in during Alpha. Tracked as a follow-up to RD-562.
Example prompts
- Refactor this Go function to use generics and explain the trade-offs.
- Summarise this 200k-token contract into a one-page brief with redlines highlighted.