ModelPriceWatch.com
Last scan 2026-08-01 Models tracked 181 Providers 27 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

Llama 3.1 8B

by Meta · 8B parameters

Current open weights open weights cheap tier

Today's price · per 1M tokens

Input

$0.050

per 1M tokens

Output

$0.080

per 1M tokens

Blended

$0.065

avg of input & output $/1M

Source: official Meta pricing · read Jun 25, 2026 MODELPRICEWATCH.COM · 2026-08-01

Overview

Small, fast open-weights model. Cheapest hosted price via Groq: $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

struck through = not supported
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

accuracy % · higher is better
Avg benchmark score34%
Perf per $/Mtok523.1
GPQA Diamond
30%
SWE-Bench Verified
12%
Humanity's Last Exam
5%
ARC-AGI 2
6%
AIME 2025
20%
MMMLU
65%
BFCL
48%
HumanEval
72%
MATH 500
48%
How it stacks up
  • Ranks #67 of 68 benchmarked models by average score
  • Ranks #126 of 133 comparably-measured models by percentile score, across 9 independent measurements
  • Ranks #25 of 133 comparably-tested models by normalized performance per dollar
  • Strongest at HumanEval — 72%, #38 of 45

1800 tokens/sec output 0.32s latency to first token (TTFT)

Source: Vellum LLM Leaderboard (Jun 2026), Kaggle dataset · updated Jun 9, 2026 · See full rankings →

Specifications

Provider
Meta
Context window
128K tokens
Modality
text
Parameters
8B
Open source
Yes — open weights available
Released
Jul 23, 2024
Status
Current
Last updated
Jun 25, 2026
Tags
open-weightsfast

Availability verified: Jul 25, 2026 — listed on Meta's own page