← model directory

meta-llama

Meta: Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct

↓ runs free on your own hardware⚙ tool calling

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...

specs & pricing
Type
text
Provider
meta-llama
Model ID
meta-llama/llama-3.3-70b-instruct
Capabilities
tools
Context window
131K tokens
Self-hostable
Yes — runs on your own GPU
Input price
$0.11 / 1M tokens
Output price
$0.35 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

What it costs to run

cloud · 1M in + 1M out

$0.46

$0.11 for a million input tokens plus $0.35 for a million output tokens, billed from credits only when a request fails over to the cloud.

your hardware

$0 / token

Served from a workstation or on-prem server you own, there is no per-token fee — the marginal cost is power.

Run it on your own hardware

Estimated GPU memory for Meta: Llama 3.3 70B Instruct (71B parameters), including the KV cache for a 8,192-token context.

Q4_K_M
~43.3 GBfits a 48 GB card
Q8_0
~72.9 GBfits a 80 GB card
FP16 / BF16
~134.7 GBmulti-GPU or large unified memory

Install the agent on the machine and it dials out to the gateway over a single WebSocket — no port forwarding or inbound firewall rules. Requests for this model go to your node first and fail over to the cloud only when it can't serve.

/// initialize

Call Meta: Llama 3.3 70B Instruct through one OpenAI-compatible endpoint.

Serve it from hardware you own, with cloud failover when your nodes are busy or offline.

no credit card · 2 nodes free · openai-compatible

Frequently asked questions

What is the context window of Meta: Llama 3.3 70B Instruct?
Meta: Llama 3.3 70B Instruct accepts up to 131,072 tokens (131K) of context per request.
How much does Meta: Llama 3.3 70B Instruct cost per million tokens?
Through Wide Area Intelligence, Meta: Llama 3.3 70B Instruct costs $0.11 per 1M input tokens and $0.35 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $0.46.
Can I run Meta: Llama 3.3 70B Instruct on my own hardware?
Yes — Meta: Llama 3.3 70B Instruct is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 43.3 GB of GPU memory with an 8,192-token context — it fits a single 48 GB card. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

More from meta-llama

← browse all models