GLM 4.6V Flash
Lightweight GLM vision model for visual reasoning, documents, and multimodal agents
Context
200,000
Max output
64,000
Input / 1M
$0.02
Output / 1M
$0.21
Providers
3
01Profile
Profile
Released
2025-12-08
Last updated
2025-12-08
Knowledge cutoff
—
Weights
Open
02Capabilities
Capabilities
Input
text · image · video · pdf
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Attachments
Yes
Cache read
—
Cache write
—
03Pricing
Pricing across 2 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2025-12-08
2026-08-19Addedempiriolabsoffering→ new
2026-08-19Addedhuggingfaceoffering→ new
2026-08-19ContextvercelContext window128,000→ new
2026-08-19Removedvercelofferingremoved→ new
2026-06-29Removedllmgatewayofferingremoved→ new
2026-04-25Removedzhipuai-coding-planofferingremoved→ new
2026-04-18Price upllmgatewayinput / 1MNot listed→ new
2026-04-18Price upllmgatewayinput / 1M—→ Not listed
2026-04-18Price upllmgatewayoutput / 1MNot listed→ new
2026-04-18Price upllmgatewayoutput / 1M—→ Not listed
2026-04-18ContextllmgatewayContext window128,000→ new
2026-04-18ContextllmgatewayContext window—→ 128,000