Galadriel's distributed infrastructure offers developers both cost savings and unlimited scalability.
Apply here to use inference in "Infinite" scale.
Model
Tier
Price per 1M input tokens
Price per 1M output tokens
RPM ¹
RPD ²
TPM ³
TPD ⁴
Llama 8B
“Free”
-
-
60
28,800
40k
5M
Llama 8B
“Infinite”
$0.035
$0.035
Llama 70B
“Free”
-
-
60
28,800
40k
5M
Llama 70B
“Infinite”
$0.25
$0.25
Llama 405B
“Free”
-
-
12
6,000
40k
1M
Llama 405B
“Infinite”
$1.5
$1.5
(1) RPM: Request Per Minute
(2) RPD: Request Per Day
(3) TPM: Tokens Per Minute
(4) TPD: Tokens Per Day
Model
Tier
Price per 1M input tokens
Price per 1M output tokens
RPM ¹
RPD ²
TPM ³
TPD ⁴
Llama 8B
“Free”
-
-
60
28,800
40k
5M
Llama 8B
“Infinite”
$0.035
$0.035
Llama 70B
“Free”
-
-
60
28,800
40k
5M
Llama 70B
“Infinite”
$0.25
$0.25
Llama 405B
“Free”
-
-
12
6,000
40k
1M
Llama 405B
“Infinite”
$1.5
$1.5
(1) RPM: Request Per Minute
(2) RPD: Request Per Day
(3) TPM: Tokens Per Minute
(4) TPD: Tokens Per Day
Model
Tier
Price per 1M input tokens
Price per 1M output tokens
RPM ¹
RPD ²
TPM ³
TPD ⁴
Llama 8B
“Free”
-
-
60
28,800
40k
5M
Llama 8B
“Infinite”
$0.035
$0.035
Llama 70B
“Free”
-
-
60
28,800
40k
5M
Llama 70B
“Infinite”
$0.25
$0.25
Llama 405B
“Free”
-
-
12
6,000
40k
1M
Llama 405B
“Infinite”
$1.5
$1.5
(1) RPM: Request Per Minute
(2) RPD: Request Per Day
(3) TPM: Tokens Per Minute
(4) TPD: Tokens Per Day