GLM 4.6
by Z.aitext->text5 endpoints
Neura Intelligence Index
58.1/ 100
Rank
#124—
Confidence
mediumBenchmarks
6(15% coverage)
Overview
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...
Capabilities
Text generation
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Modalities
Input
Text
Output
Text
Technical Specifications
Context Window
202.8K tokens
Max Output
131.1K tokens
Knowledge Cutoff
2025-03-31
Tokenizer
Other
Uptime (24h)
9992.6%
Parameters
357000000000B
License
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Benchmark Performance
coding
| Benchmark | Score | Source |
|---|---|---|
| SWE-bench Verified | 68 | verified |
| TerminalBench | 40.5 | verified |
math
| Benchmark | Score | Source |
|---|---|---|
| AIME 2025 | 93.9 | verified |
reasoning
Performance Over Time
Pricing
Per 1M tokens
Input$0.50
Output$2.00
Cache read$0.10