Llama 3.2 3B Instruct
Open Llama instruction model for multilingual chat, reasoning, and coding
Context
131,072
Max output
117,964
Input / 1M
$0.02
Output / 1M
$0.02
Providers
10
01Profile
Profile
Released
2024-09-25
Last updated
2025-01-01
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 9 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2024-09-25
2026-08-25ContextkiloMax output131,072→ 117,964
2026-08-25ContextopenrouterMax output131,072→ 117,964
2026-08-24Removedcloudflare-ai-gatewayofferingremoved→ new
2026-08-20Addedllmgateway-providersoffering→ new
2026-08-14Price cutcloudflare-ai-gatewayinput / 1M$0.05→ $0.05
2026-08-14Price cutcloudflare-ai-gatewayoutput / 1M$0.34→ $0.34
2026-08-14Contextcloudflare-ai-gatewayContext window128,000→ 80,000
2026-08-14Contextcloudflare-ai-gatewayMax output16,384→ 80,000
2026-08-02Price cutkiloinput / 1M$0.05→ $0.05
2026-08-02Price cutkilooutput / 1M$0.34→ $0.33
2026-08-02ContextkiloContext window80,000→ 131,072
2026-08-02ContextkiloMax output16,384→ 131,072
05Usage
Monthly token share
Rank #66 · 2025-09
0.0%