LIVE Cheapest paid: Granite 4.0 Micro $0.017/Mtok in 173 models tracked Updated Jul 10, 2026
Jul 10, 2026
ModelPriceWatch$/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
$0.080
per million tokens
Blended avg cost*$0.065/Mtok

Overview

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

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

Input 1/5
Text ✓ Image Audio Video PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 3/9
Prompt caching Reasoning Coding Fast inference ✓ Long context ✓ Open weights ✓ Multimodal Web search Realtime

Benchmark performance

34%
avg benchmark score
64.8
perf / $/Mtok
GPQA Diamond
30%
AIME 2025
20%
SWE-Bench
12%
Humanity's Last Exam
5%
ARC-AGI 2
6%
MMMLU
65%
HumanEval
72%
MATH 500
48%
BFCL
48%
How it stacks up
  • Ranks #35 of 35 benchmarked models by average score
  • Ranks #26 of 35 comparably-tested models by normalized performance per dollar
  • Strongest at BFCL — 48%, #53 of 55
Inference speed: 1800 tokens/sec

Source: Groq model card · Updated Jun 1, 2026 · See full rankings →

Specifications

ProviderGroq
Context window128K tokens
Modalitytext
Parameters8B
Open sourceYes — open weights available
ReleasedJul 23, 2024
StatusCurrent
Last updatedJul 4, 2026
Tagsfast open-weights speed

Cost calculator

1K tokens (in)$0.00005
1K tokens (out)$0.00008
100K tokens (in)$0.005
100K tokens (out)$0.008
1M tokens (in)$0.050
1M tokens (out)$0.080
10M tokens (blended)$0.650
Full calculator →

At a glance

Input$0.050/M
Output$0.080/M
Blended$0.065/M
Context128K
Tiercheap

Embed this price

A live, auto-updating badge for your README or docs:

Llama 3.1 8B Instant live API price

Price history

Last updated: Jul 10, 2026 · price links to the official provider pricing page (source above)

Jul 4, 2026 ↓ $0.05/$0.08/M
Jun 25, 2026 $0.05/$1/M
Oct 8, 2024 $0.05/$0.08/M
Jul 29, 2024 $0.59/$0.79/M

3 price changes recorded since Jul 29, 2024

Compare Llama 3.1 8B Instant

Featured in these rankings

Related models