Meta

Llama 3.3 70B Instruct API Pricing

Aggregator pricing; Meta does not sell a first-party priced API (llama.developer.meta.com is waitlist-only with no published pricing). A free-tier variant with usage limits is also listed by the aggregator.

Verified against Meta’s pricing page on 2026-07-02.

View source ↗

Facts

Legacy

Specs

  • FamilyLlama 3
  • API IDmeta-llama/llama-3.3-70b-instruct
  • ModalityText
  • Context window131K tokens
  • Max output
  • Release dateNot published

Pricing (per 1M tokens)

  • Input$0.10 / 1M tokens
  • Output$0.32 / 1M tokens
  • Cached input
  • Cache write
  • Batch discount

Capabilities

tool-use

Notes

Aggregator pricing; Meta does not sell a first-party priced API (llama.developer.meta.com is waitlist-only with no published pricing). A free-tier variant with usage limits is also listed by the aggregator.

Worked cost examples

Estimated monthly cost on three common usage shapes

WorkloadEst. monthly cost

Chatbot

800 input / 200 output tokens per request, 100,000 requests/month

$14.40

RAG pipeline

6,000 input / 700 output tokens per request, 30,000 requests/month

$24.72

Batch summarization

20,000 input / 1,500 output tokens per request, 5,000 requests/month

$12.40

Price history

Changes we have documented since we began tracking

No price changes recorded since we began tracking.

Llama 3.3 70B Instruct pricing FAQ

How much does Llama 3.3 70B Instruct cost per 1M tokens?
Llama 3.3 70B Instruct costs $0.10 per 1M input tokens and $0.32 per 1M output tokens.
How much does Llama 3.3 70B Instruct cost per request?
A typical request of 800 input and 200 output tokens costs about $0.000144 on Llama 3.3 70B Instruct.
Is Llama 3.3 70B Instruct cheaper than Llama 4 Maverick?
Llama 3.3 70B Instruct is cheaper than Llama 4 Maverick on input tokens, by about 33%.
Does Llama 3.3 70B Instruct have cache pricing?
No cache discount is documented for Llama 3.3 70B Instruct on the provider's pricing page.