granite familyActive
Granite 4.0 H Micro
Efficient model for low-latency assistance, extraction, and routine automation
Context
131,000
Max output
131,000
Input / 1M
$0.02
Output / 1M
$0.11
Providers
3
01Profile
Profile
Released
2025-10-07
Last updated
2025-10-20
Knowledge cutoff
—
Weights
Open
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
No
Tool calling
Yes
Structured output
No
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 3 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2025-10-07
2026-08-25ContextkiloMax output131,000→ 117,900
2026-08-25ContextopenrouterMax output131,000→ 117,900
2026-08-24Removedcloudflare-ai-gatewayofferingremoved→ new
2026-08-14Price upcloudflare-ai-gatewayoutput / 1M$0.11→ $0.11
2026-08-14Contextcloudflare-ai-gatewayContext window128,000→ 131,000
2026-08-14Contextcloudflare-ai-gatewayMax output16,384→ 131,000
2026-08-02Price upkilooutput / 1M$0.11→ $0.11
2026-08-02ContextkiloMax output32,768→ 131,000
2026-05-20Addedcloudflare-workers-aioffering→ new
2026-05-16Price upopenrouteroutput / 1M$0.11→ $0.11
2026-05-15Addedopenrouteroffering→ new
2026-04-07Removedcloudflare-workers-aiofferingremoved→ new