Llama 3.3 70B Instruct

MetaOpen weights131K context

LMArena score 1274 · #275 overall · #283 in coding (2026-10-13)

Lowest price, from Hyperbolic

Per million tokens

Input: $0.12
Output: $0.30
Cached input: —
Batch input / output: —

Up to 131K output tokens per request.

Estimate your monthly cost

Input per month

M tokens

Output per month

M tokens

Input served from cache

Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.

From Hyperbolic: $1.80 a month.

Where to buy it (17)

Sorted by your monthly estimate. Prices per million tokens.

Seller	Input	Output	Cached input	Context	Est. per month10M in · 2M out
HyperbolicCheapest hyperbolic/meta-llama/Llama-3.3-70B-Instruct	$0.12	$0.30	—	131K	$1.80
Nebius nebius/meta-llama/Llama-3.3-70B-Instruct	$0.13	$0.40	—	131K	$2.10
Novita AI novita/meta-llama/llama-3.3-70b-instruct	$0.135	$0.40	—	12K	$2.15
Crusoe crusoe/meta-llama/Llama-3.3-70B-Instruct	$0.20	$0.20	—	131K	$2.40
Nscale nscale/meta-llama/Llama-3.3-70B-Instruct	$0.20	$0.20	—	—	$2.40
DeepInfra deepinfra/meta-llama/Llama-3.3-70B-Instruct	$0.23	$0.40	—	131K	$3.10
Gradient Ai gradient_ai/llama3.3-70b-instruct	$0.65	$0.65	—	128K	$7.80
Microsoft Foundry azure_ai/Llama-3.3-70B-Instruct	$0.71	$0.71	—	128K	$8.52
W&B Inference wandb/meta-llama/Llama-3.3-70B-Instruct	$0.71	$0.71	—	128K	$8.52
Amazon Bedrock Converse meta.llama3-3-70b-instruct-v1:0	$0.72	$0.72	—	128K	$8.64
Oracle Cloud oci/meta.llama-3.3-70b-instruct	$0.72	$0.72	—	128K	$8.64
Snowflake snowflake/llama3.3-70b	$0.72	$0.72	—	128K	$8.64
Vercel AI Gateway vercel_ai_gateway/meta/llama-3.3-70b	$0.72	$0.72	—	128K	$8.64
Google Vertex AI vertex_ai/meta/llama-3.3-70b-instruct-maas	$0.72	$0.72	—	128K	$8.64
IBM watsonx watsonx/meta-llama/llama-3-3-70b-instruct	$0.7526	$0.7526	—	131K	$9.03
Scaleway scaleway/meta/llama-3.3-70b-instruct	$0.90	$0.90	—	128K	$10.80
Cerebras cerebras/llama-3.3-70b	$0.85	$1.20	—	128K	$10.90

HyperbolicCheapest
Input / output
$0.12 / $0.30
Context
131K
Per month
$1.80
hyperbolic/meta-llama/Llama-3.3-70B-Instruct
Nebius
Input / output
$0.13 / $0.40
Context
131K
Per month
$2.10
nebius/meta-llama/Llama-3.3-70B-Instruct
Novita AI
Input / output
$0.135 / $0.40
Context
12K
Per month
$2.15
novita/meta-llama/llama-3.3-70b-instruct
Crusoe
Input / output
$0.20 / $0.20
Context
131K
Per month
$2.40
crusoe/meta-llama/Llama-3.3-70B-Instruct
Nscale
Input / output
$0.20 / $0.20
Context
—
Per month
$2.40
nscale/meta-llama/Llama-3.3-70B-Instruct
DeepInfra
Input / output
$0.23 / $0.40
Context
131K
Per month
$3.10
deepinfra/meta-llama/Llama-3.3-70B-Instruct
Gradient Ai
Input / output
$0.65 / $0.65
Context
128K
Per month
$7.80
gradient_ai/llama3.3-70b-instruct
Microsoft Foundry
Input / output
$0.71 / $0.71
Context
128K
Per month
$8.52
azure_ai/Llama-3.3-70B-Instruct
W&B Inference
Input / output
$0.71 / $0.71
Context
128K
Per month
$8.52
wandb/meta-llama/Llama-3.3-70B-Instruct
Amazon Bedrock Converse
Input / output
$0.72 / $0.72
Context
128K
Per month
$8.64
meta.llama3-3-70b-instruct-v1:0
Oracle Cloud
Input / output
$0.72 / $0.72
Context
128K
Per month
$8.64
oci/meta.llama-3.3-70b-instruct
Snowflake
Input / output
$0.72 / $0.72
Context
128K
Per month
$8.64
snowflake/llama3.3-70b
Vercel AI Gateway
Input / output
$0.72 / $0.72
Context
128K
Per month
$8.64
vercel_ai_gateway/meta/llama-3.3-70b
Google Vertex AI
Input / output
$0.72 / $0.72
Context
128K
Per month
$8.64
vertex_ai/meta/llama-3.3-70b-instruct-maas
IBM watsonx
Input / output
$0.7526 / $0.7526
Context
131K
Per month
$9.03
watsonx/meta-llama/llama-3-3-70b-instruct
Scaleway
Input / output
$0.90 / $0.90
Context
128K
Per month
$10.80
scaleway/meta/llama-3.3-70b-instruct
Cerebras
Input / output
$0.85 / $1.20
Context
128K
Per month
$10.90
cerebras/llama-3.3-70b

Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: Tool calling.

Lowest price, from Hyperbolic

Estimate your monthly cost

Where to buy it (17)

Similar models