Llama 3.3 70B Instruct fp8 Fast
Popular open Llama workhorse for multilingual chat, coding, and self-hosting
Context
24,000
Max output
24,000
Input / 1M
$0.29
Output / 1M
$2.25
Providers
1
01Profile
Profile
Released
2024-12-06
Last updated
2024-12-06
Knowledge cutoff
2023-12
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 1 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2024-12-06
2026-08-24Removedcloudflare-ai-gatewayofferingremoved→ new
2026-08-14Price upcloudflare-ai-gatewayinput / 1M$0.29→ $0.29
2026-08-14Price upcloudflare-ai-gatewayoutput / 1M$2.25→ $2.25
2026-08-14Contextcloudflare-ai-gatewayContext window128,000→ 24,000
2026-08-14Contextcloudflare-ai-gatewayMax output16,384→ 24,000
2026-05-20Addedcloudflare-workers-aioffering→ new
2026-04-07Removedcloudflare-workers-aiofferingremoved→ new
2025-12-23Price upcloudflare-ai-gatewayinput / 1MNot listed→ $0.29
2025-12-12Price upcloudflare-ai-gatewayinput / 1MNot listed→ $290000.00
2025-12-12Price upcloudflare-ai-gatewayoutput / 1M$2.25→ $2250000.00
2025-12-07Price cutcloudflare-ai-gatewayinput / 1M$0.29→ $-6999996.96
2025-12-07Price upcloudflare-ai-gatewayinput / 1M$-6999996.96→ Not listed