groq

llama-3.1-8b-instant

Context

128K

Input

text

Output

text

Tool calling

Supported

About this model

Llama 3.1 8B Instruct is Meta's instruction-tuned 8-billion parameter language model featuring 128K context length, enhanced reasoning capabilities, and improved performance across coding, mathematics, and instruction following tasks. Optimized for chat and dialogue applications.

Capabilities

text

Available through the unified API

Quick start

View API docs
curl https://api.oneinfer.ai/v1/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "2dba2b4d7f51415a8499576a892e1f53",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

Providers

Available routing options for this model through OneInfer.

groq

2dba2b4d7f51415a8499576a892e1f53

Available

Input

$0.050 / 1M

Output

$0.080 / 1M

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$0.050 / 1M
Output tokens$0.080 / 1M

Performance

Published evaluation results associated with this model.

General Knowledge

MMLU68.4
HellaSwag82.7
ARC-Challenge76.9
Winogrande74.3

Mathematical Reasoning

GSM8K79.8
MATH38.5
AQuA-RAT42.7

Coding Tasks

HumanEval58.3
MBPP52.9
LiveCodeBench41.6

Instruction Following

IFEval72.8
AlpacaEval81.5
MT-Bench7.2

Multilingual Tasks

MGSM62.4
XCOPA76.8
FLORES58.9

Reasoning & Safety

BBH65.7
TruthfulQA48.3
BOLD85.2

Long Context Performance

NeedleInAHaystack96.3
ZeroSCROLLS68.9
LongBench62.7

API example

curl https://api.oneinfer.ai/v1/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "2dba2b4d7f51415a8499576a892e1f53",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'