Scheduled for retirement on Oct 21, 2026. Still available at the prices below until then.
Context
128K
Max output
8K
Serving providers
1
Cheapest input
$0.72 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Vertex AI Llama ModelsCheapest$0.72$0.721
Standardvertex_ai/meta/llama-3.3-70b-instruct-maas
ComponentUnitStandardBatch
Text input/1M tok$0.72$0.36
Text output/1M tok$0.72$0.36

Price history

listed seller prices, input and output per 1M tokens
Input Output

Price history is accruing. We record a point each day a listed seller price changes; the full backfill lands shortly.

Cost calculator

estimate your monthly spend on this model
$202
estimated / month

Model IDs

copy the exact identifier for your platform
vertex_ai/meta/llama-3.3-70b-instruct-maas

Frequently asked questions

Llama 3.3 70B Instruct Maas pricing, context and availability

Is Llama 3.3 70B Instruct Maas still available?

Yes. Llama 3.3 70B Instruct Maas is scheduled for retirement on 2026-10-21.

How much does Llama 3.3 70B Instruct Maas cost?

Llama 3.3 70B Instruct Maas costs $0.72 per 1M input tokens from Vertex AI Llama Models, and $0.72 per 1M output tokens from Vertex AI Llama Models.

What is the context window of Llama 3.3 70B Instruct Maas?

Llama 3.3 70B Instruct Maas accepts up to 128K tokens of context and can return up to 8K output tokens.

What can Llama 3.3 70B Instruct Maas do?

Llama 3.3 70B Instruct Maas supports tool use.

Other Meta models

compare pricing across the Meta lineup
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI