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

by Meta · 70B parameters

Current open weights open weights cheap tier
Email me when Llama 3.3 70B gets cheaper

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 Meta pricing · read Jun 25, 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

Widely used open-weights model. Cheapest hosted price via Groq: $0.59/$0.79 per 1M tokens (also on Together at $1.04/$1.04).

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.

RunPod →
Rent GPUs by the second and serve any open-weight model yourself.
Novita AI →
Serverless open-model inference billed per token — no GPU ops.
Vast.ai →
GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

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 2/9
Prompt caching Reasoning Coding Fast inference Long context ✓ Open weights ✓ Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
Avg benchmark score46.6%
Perf per $/Mtok67.5
GPQA Diamond
50.5%
SWE-Bench Verified
22%
Humanity's Last Exam
10%
ARC-AGI 2
12%
AIME 2025
38%
MMMLU
72%
BFCL
77.3%
HumanEval
78%
MATH 500
60%
How it stacks up
  • Ranks #59 of 68 benchmarked models by average score
  • Ranks #96 of 133 comparably-measured models by percentile score, across 9 independent measurements
  • Ranks #45 of 133 comparably-tested models by normalized performance per dollar
  • Strongest at BFCL — 77.3%, #4 of 23

2500 tokens/sec output 0.52s latency to first token (TTFT)

Source: Vellum LLM Leaderboard · updated Aug 1, 2026 · See full rankings →

Specifications

Provider
Meta
Context window
128K tokens
Modality
text
Parameters
70B
Open source
Yes — open weights available
Released
Dec 6, 2024
Status
Current
Last updated
Jun 25, 2026
Tags
open-weights

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

Official pricing page