GLM 5.2
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
Context
1,048,575
Max output
131,072
Input / 1M
$1.40
Output / 1M
$4.40
Providers
1
01Profile
Profile
Released
2026-06-16
Last updated
2026-06-16
Knowledge cutoff
—
Weights
Open
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
No
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 1 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
4+ recent events since 2026-06-16
2026-07-01Contextfireworks-aiContext window1,048,576→ 1,048,575
2026-06-26Contextfireworks-aiContext window1,048,576→ 1,048,575
2026-06-26Contextfireworks-aiContext window1,048,575→ 1,048,576
2026-06-17Addedfireworks-aioffering→ new