Llama 3.1 8B Instruct fp8
Open Llama instruction model for multilingual chat, reasoning, and coding
Context
128,000
Max output
32,000
Input / 1M
$0.02
Output / 1M
$0.03
Providers
2
01Profile
Profile
Released
2024-07-23
Last updated
2024-07-23
Knowledge cutoff
2023-12
Weights
Open
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
No
Tool calling
No
Structured output
No
Attachments
No
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 2024-07-23
2026-08-24Removedcloudflare-ai-gatewayofferingremoved→ new
2026-08-14Price upcloudflare-ai-gatewayinput / 1M$0.15→ $0.15
2026-08-14Price cutcloudflare-ai-gatewayoutput / 1M$0.29→ $0.29
2026-08-14Contextcloudflare-ai-gatewayContext window128,000→ 32,000
2026-08-14Contextcloudflare-ai-gatewayMax output16,384→ 32,000
2026-07-01Addedstackitoffering→ new
2026-06-26Removedstackitofferingremoved→ new
2026-06-11Price upstackitinput / 1M$0.16→ $0.18
2026-06-11Price upstackitoutput / 1M$0.27→ $0.29
2026-06-11ContextstackitMax output8,192→ 4,096
2026-06-11DeprecatedstackitStatus—→ deprecated
2026-05-20Addedcloudflare-workers-aioffering→ new