LIVE Cheapest paid: Granite 4.0 Micro $0.017/Mtok in 173 models tracked Updated Jul 10, 2026
Jul 10, 2026
ModelPriceWatch$/Mtok
Pricing / Meta / Llama 3.3 70B

Llama 3.3 70B

by Meta · 70B parameters

Current open weights Open weights cheap tier

Pricing · per 1M tokens

Input
$0.590
per million tokens
Output
$0.790
per million tokens
Blended avg cost*$0.690/Mtok

Available on 3 hosts · cheapest first

Llama 3.3 70B is sold by 3 providers. Prices are per 1M tokens (blended = avg of input & output). The first-party row is the model maker; “vs first-party” shows each host’s blended price relative to it.

Host Input Output Blended vs first-party
Groq details → $0.590 $0.790 $0.690 0%
Meta first-party $0.590 $0.790 $0.690
Together details → $1.04 $1.04 $1.04 +51%

Each host links to its provider page and official pricing. Prices refresh twice daily.

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.

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

Benchmark performance

43.6%
avg benchmark score
63.2
perf / $/Mtok
GPQA Diamond
45%
AIME 2025
38%
SWE-Bench
22%
Humanity's Last Exam
10%
ARC-AGI 2
12%
MMMLU
72%
HumanEval
78%
MATH 500
60%
BFCL
55%
How it stacks up
  • Ranks #31 of 35 benchmarked models by average score
  • Ranks #16 of 35 comparably-tested models by normalized performance per dollar
  • Strongest at ARC-AGI 2 — 12%, #47 of 59
Inference speed: 2500 tokens/sec

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

Specifications

ProviderMeta
Context window128K tokens
Modalitytext
Parameters70B
Open sourceYes — open weights available
ReleasedDec 6, 2024
StatusCurrent
Last updatedJun 25, 2026
Tagsopen-weights

Cost calculator

1K tokens (in)$0.00059
1K tokens (out)$0.00079
100K tokens (in)$0.059
100K tokens (out)$0.079
1M tokens (in)$0.590
1M tokens (out)$0.790
10M tokens (blended)$6.90
Full calculator →

At a glance

Input$0.590/M
Output$0.790/M
Blended$0.690/M
Context128K
Tiercheap

Embed this price

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

Llama 3.3 70B live API price

Price history

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

No price changes detected — this model's pricing has been stable since we began tracking it.

Compare Llama 3.3 70B

Related models