GLM-5.3-Flash
Native multimodal GLM model for efficient coding and long-horizon agent tasks
Context
1,310,720
Max output
1,048,576
Input / 1M
$0.01
Output / 1M
$0.03
Providers
53
01Profile
Profile
Released
2026-08-26
Last updated
2026-09-01
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
$0.01
Cache write
Not listed
03Pricing
Pricing across 54 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2026-08-26
2026-09-16Price upopenrouterinput / 1M$0.07→ $0.10
2026-09-16Price upopenrouteroutput / 1M$0.25→ $0.33
2026-09-15Price cutopenrouterinput / 1M$0.15→ $0.07
2026-09-15Price cutopenrouteroutput / 1M$0.50→ $0.25
2026-09-14Addedfriendlioffering→ new
2026-09-14Addedmeliousoffering→ new
2026-09-14Price upollama-cloudinput / 1M—→ $0.15
2026-09-14Price upollama-cloudoutput / 1M—→ $0.50
2026-09-14Price upvancineinput / 1M$0.06→ $0.12
2026-09-14Price upvancineoutput / 1M$0.20→ $0.40
2026-09-13ContextkiloMax output—→ 943,718
2026-09-13ContextkiloMax output943,718→ new