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 3.3 70B Versatile

by Groq · 70B parameters

Deprecated fast open weights 394 TPS cheap tier
Deprecated — shuts down Aug 16, 2026. Still purchasable until then, but the provider has announced end-of-life. Don't start new work on it. Migration target: GPT-OSS 120B.
Availability: Groq shutdown 2026-08-16.

Today's price · per 1M tokens

Input

$0.590

per 1M tokens

Output

$0.790

per 1M tokens

Blended

$0.690

avg of input & output $/1M

Source: official Groq pricing · read Jul 4, 2026 MODELPRICEWATCH.COM · 2026-08-01
Llama 3.3 70B is available on 3 hosts. See the full cheapest-first comparison on the consolidated Llama 3.3 70B page →

Overview

Llama 3.3 70B on Groq's LPU. ~394 tokens/sec. $0.59/$0.79 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 score43.6%
Perf per $/Mtok63.2
GPQA Diamond
45%
SWE-Bench Verified
22%
Humanity's Last Exam
10%
ARC-AGI 2
12%
AIME 2025
38%
MMMLU
72%
BFCL
55%
HumanEval
78%
MATH 500
60%
How it stacks up
  • Ranks #62 of 68 benchmarked models by average score
  • Ranks #107 of 133 comparably-measured models by percentile score, across 9 independent measurements
  • Ranks #71 of 133 comparably-tested models by normalized performance per dollar
  • Strongest at HumanEval — 78%, #30 of 45

2500 tokens/sec output

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

Specifications

Provider
Groq
Context window
128K tokens
Modality
text
Parameters
70B
Open source
Yes — open weights available
Released
Dec 6, 2024
Status
Deprecated ends Aug 16, 2026
Last updated
Jul 4, 2026
Tags
fastopen-weightsspeed

Availability verified: Jul 25, 2026 — per Groq's own deprecation notice