LIVE Cheapest: GLM-4.7-Flash $0.000/Mtok in 153 models tracked Updated Jun 24, 2026
Jun 24, 2026
ModelPriceWatch$/Mtok
Pricing / Groq / Llama 3.1 8B Instant

Llama 3.1 8B Instant

by Groq · 8B parameters

Current fast Open weights 840 TPS cheap tier

Pricing · per 1M tokens

Input
$0.050
per million tokens
Output
$1.00
per million tokens
Blended avg cost*$0.525/Mtok

Overview

Llama 3.1 8B on Groq's LPU. ~840 tokens/sec — extremely fast. $0.05/$0.08 per 1M tokens.

Specifications

ProviderGroq
Context window128K tokens
Modalitytext
Parameters8B
Open sourceYes — open weights available
ReleasedJul 23, 2024
StatusCurrent
Last updatedJun 24, 2026
Tagsfast open-weights speed

Cost calculator

1K tokens (in)$0.0001
1K tokens (out)$0.001
100K tokens (in)$0.005
100K tokens (out)$0.1
1M tokens (in)$0.050
1M tokens (out)$1.00
10M tokens (blended)$5.3
Full calculator →

At a glance

Input$0.050/M
Output$1.00/M
Blended$0.525/M
Context128K
Tiercheap

Price history

Jun 24, 2026 Baseline · $0.05/$1/M

Tracking since Jun 24, 2026 · 1 data points

Related models