Model Price Index
Updated 2026-07-14 · Changelog

Llama 3.1 8B Instant

GroqLegacy

Meta's Llama 3.1 8B running on Groq's LPU hardware for ultra-fast inference at minimal cost

$0.05

Input

$0.08

Output

per 1M tokens

Ratesper 1M tokens

Input$0.05
Output$0.08

Estimate Your Monthly Cost

A request with input and output tokens, requests / month at a % cache hit rate $4.00/mo

Compare all models at this workload →

Excludes cache writes and batch discounts.

Specifications

API Model IDllama-3.1-8b-instant
Context Window128K tokens
Max Output8K tokens
Modalitiestext
Capabilitiestool-use · streaming · json-mode · code

More Groq Text / Chat Models

GPT OSS 20B · Llama 4 Scout · GPT OSS 120B · Llama 4 Maverick · Qwen3 32B · Llama 3.3 70B Versatile · Kimi K2 · GPT OSS Safeguard 20B ·