Compact open Llama model for lightweight chat, drafting, and self-hosting
Specification
most-agreed values
Context
131K
Max output
16K
Released
2024-07-23
Knowledge cutoff
2023-12
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.0544
Output
$0.085
Cache read
$0.0272
Cache write
$0.20
Available from 19 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| nvidia | free | free | — | — | 16K | 4K | — |
| helicone | $0.02 | $0.05 | — | — | 16K | 16K | — |
| kilo · meta-llama | $0.02 | $0.04 | — | — | 131K | 118K | — |
| novita | $0.02 | $0.05 | — | — | 16K | 16K | — |
| novita-ai · meta-llama | $0.02 | $0.05 | — | — | 16K | 16K | — |
| inference | $0.025 | $0.025 | — | — | 16K | 4K | — |
| nscale | $0.03 | $0.03 | — | — | — | — | — |
| openrouter | $0.05 | $0.08 | $0.025 | — | 131K | 118K | — |
| openrouter · meta-llama | $0.05 | $0.08 | $0.025 | — | 131K | 118K | — |
| nano-gpt · meta-llama | $0.0544 | $0.085 | $0.0272 | — | 131K | 16K | — |
| huggingface · meta-llama | $0.06 | $0.06 | — | — | 131K | 4K | — |
| ovhcloud · ovhcloud | $0.10 | $0.10 | — | — | 131K | 131K | — |
| cortecs | $0.167 | $0.167 | — | — | 128K | 128K | — |
| perplexity | $0.20 | $0.20 | — | — | 131K | 131K | — |
| pioneer · meta-llama | $0.20 | $0.20 | $0.20 | $0.20 | 128K | 8K | — |
| merge-gateway | $0.22 | $0.22 | — | — | 128K | 2K | — |
| wandb · meta-llama | $0.22 | $0.22 | $0.22 | — | 131K | 131K | — |
| wandb · wandb | $0.22 | $0.22 | — | — | 128K | 128K | — |
| oci · oci | $0.72 | $0.72 | — | — | 128K | 4K | — |
Other listings of this model
same model, different key
More from Meta
most-hosted first