Llama 3.3 70B Instruct

Metatext → textHugging Face OpenRouter

The cheapest provider for Llama 3.3 70B Instruct is DeepInfra at $0.155 per 1M tokens (blended), charging $0.10 per 1M input and $0.32 per 1M output tokens. 10 providers serve it; the most expensive charges 6.7× as much. Context window: 128K tokens. Prices tracked since Oct 3, 2026.

Best price

$0.155

at DeepInfra

Input / output

$0.10 / $0.32

per 1M tokens

Providers

6.7× spread

7 days

—

best price

30 days

—

best price

Context

128K

tokens

Providers

Active offers ranked by blended price. Bars are relative to the most expensive.

Provider prices for Meta: Llama 3.3 70B Instruct, USD per 1M tokens
Provider	Input	Output	Blended	vs cheapest	Context	Uptime 1d	Price since
DeepInfraturboCheapest fp8	$0.10	$0.32	$0.155	best	128K	98.5%	Oct 3
Novita bf16	$0.135	$0.40	$0.201	+30%	12K	89.5%	Oct 3
AkashML fp8	$0.20	$0.52	$0.28	+81%	128K	99.5%	Oct 3
Parasail fp8	$0.22	$0.50	$0.29	+87%	128K	99.3%	Oct 3
SambaNova −25% discount	$0.45	$0.90	$0.563	+263%	128K	98.6%	Oct 3
Groq	$0.59	$0.79	$0.64	+313%	128K	99.8%	Oct 3
CoreWeave fp16	$0.71	$0.71	$0.71	+358%	125K	99.8%	Oct 3
Google	$0.72	$0.72	$0.72	+365%	125K	—	Oct 3
Googleus-central1	$0.72	$0.72	$0.72	+365%	125K	—	Oct 3
Cloudflare fp8	$0.293	$2.253	$0.783	+405%	24K	99.1%	Oct 3
Together	$1.04	$1.04	$1.04	+571%	128K	98.0%	Oct 3

DeepInfraCheapest
turbo
$0.155
$0.10 in · $0.32 out
best
128K ctx98.5% uptimefp8
Novita
$0.201
$0.135 in · $0.40 out
+30%
12K ctx89.5% uptimebf16
AkashML
$0.28
$0.20 in · $0.52 out
+81%
128K ctx99.5% uptimefp8
Parasail
$0.29
$0.22 in · $0.50 out
+87%
128K ctx99.3% uptimefp8
SambaNova
$0.563
$0.45 in · $0.90 out
+263%
128K ctx98.6% uptime−25% discount
Groq
$0.64
$0.59 in · $0.79 out
+313%
128K ctx99.8% uptime
CoreWeave
$0.71
$0.71 in · $0.71 out
+358%
125K ctx99.8% uptimefp16
Google
$0.72
$0.72 in · $0.72 out
+365%
125K ctx
Google
us-central1
$0.72
$0.72 in · $0.72 out
+365%
125K ctx
Cloudflare
$0.783
$0.293 in · $2.253 out
+405%
24K ctx99.1% uptimefp8
Together
$1.04
$1.04 in · $1.04 out
+571%
128K ctx98.0% uptime

Blended = (3 × input + output) / 4.

Price history

Hover to compare providers at any point in time. Click a legend item to hide it.

USD per 1M tokens · each step is a price change

Not enough history yet

Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.

Other pricing

Cache, reasoning and per-call fees. Token rates per 1M; others per unit.

Offered by	Cache read
AkashML	$0.10
Parasail	$0.11
Groq	$0.295
CoreWeave	$0.71

Change log

Every recorded change for this model since Oct 3, 2026.

No changes yet

Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.

About this model

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Released: Dec 6, 2024
First tracked: Oct 3, 2026
Canonical slug: meta-llama/llama-3.3-70b-instruct
Weights: meta-llama/Llama-3.3-70B-Instruct