GLM 5.2
by Z.aitext->text30 endpoints
Neura Intelligence Index
73.2/ 100
Rank
#52—
Confidence
lowBenchmarks
3(8% coverage)
Overview
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
Capabilities
Text generation
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Modalities
Input
Text
Output
Text
Technical Specifications
Context Window
1.0M tokens
Max Output
131.1K tokens
Tokenizer
Other
Uptime (24h)
9997.0%
Parameters
744000000000B
License
mitOpen Weights
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Benchmark Performance
coding
| Benchmark | Score | Source |
|---|---|---|
| SWE-bench Verified | 77.8 | verified |
agent
| Benchmark | Score | Source |
|---|---|---|
| BrowseComp | 75.9 | verified |
| MCP Atlas | 67.8 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$0.82
Output$2.57
Cache read$0.15