Back to all models

Llama 3.1 8B Instruct

Compact Llama 3.1 for efficient text generation.

llama-3.1-8b-instruct
STABLE
128,000 context
Starting at $0.02/M input tokens
Starting at $0.06/M output tokens
Streaming
Tools
JSON Output

Select Provider

All Providers for Llama 3.1 8B Instruct

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

AWS Bedrock

UNSTABLE
aws-bedrock/llama-3.1-8b-instruct
Context Size
128k
Stability
unstable
Pricing
Input
$0.22
/M
Cached
—
Output
$0.22
/M
Per Request
$0.000
/req
Capabilities
Streaming
Try in Playground

Nebius AI

nebius/llama-3.1-8b-instruct
Context Size
128k
Stability
STABLE
Pricing
Input
$0.02
/M
Cached
—
Output
$0.06
/M
Per Request
$0.000
/req
Capabilities
Streaming
Try in Playground

Inference.net

UNSTABLE
inference.net/llama-3.1-8b-instruct
Context Size
128k
Stability
unstable
Pricing
Input
$0.07
/M
Cached
—
Output
$0.33
/M
Per Request
$0.000
/req
Capabilities
Streaming
Try in Playground

Together AI

together.ai/llama-3.1-8b-instruct
Context Size
128k
Stability
STABLE
Pricing
Input
$0.06
/M
Cached
—
Output
$0.06
/M
Per Request
$0.000
/req
Capabilities
Streaming
Tools
Try in Playground

Cerebras

cerebras/llama-3.1-8b-instruct
Context Size
128k
Stability
STABLE
Pricing
Input
$0.10
/M
Cached
—
Output
$0.10
/M
Per Request
$0.000
/req
Capabilities
Streaming
JSON Output
Try in Playground