Compact instruction-tuned Llama model for multilingual dialogue and on-device assistants
Specification
most-agreed values
Context
60K
Max output
32K
Released
2024-09-25
Knowledge cutoff
2023-12
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.027
Output
$0.201
Rate limits
Requests per minute
300
Available from 10 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| inference | $0.01 | $0.01 | — | — | 16K | 4K | — |
| novita | $0.02 | $0.02 | — | — | 131K | 32K | — |
| novita-ai · meta-llama | $0.02 | $0.02 | — | — | 131K | 32K | — |
| cloudflare | $0.027 | $0.201 | — | — | 60K | 60K | — |
| cloudflare-workers-ai · cf | $0.027 | $0.201 | — | — | 60K | 60K | — |
| edenai | $0.027 | $0.201 | — | — | 60K | 32K | — |
| kilo · meta-llama | $0.027 | $0.201 | — | — | 60K | 54K | — |
| openrouter · meta-llama | $0.027 | $0.201 | — | — | 60K | 54K | — |
| together_ai | $0.06 | $0.06 | — | — | 131K | 131K | — |
| watsonx | $0.10 | $0.10 | — | — | 128K | 128K | — |
More from Meta
most-hosted first