Skip to content
LLM Prices Today

Meta Llama 3.3 70B Instruct API pricing

Token prices on OpenRouter and at the provider’s list price, and what your own workload would cost per month.

Input
$0.10
Output
$0.32
Cached input
—

OpenRouter, per 1M tokens. A dash means no listed price.

Your monthly cost

Your workload

90M input and 18M output tokens a month (30-day month; token counts are per request).

Assumes: 1,000 conversations a day, each sending about 3,000 tokens of history and instructions and receiving about 600 tokens of replies.

Input not in cache
$9.00
Output
$5.76
Total per month
$14.76
Per day
$0.492
Per request
$0.00049
Unit
Currency

No cache-read price is published for this model, so a cached share is billed as normal input. Compare this bill with other models.

Every price, with its source

OpenRouter price, per 1M tokens

Input
$0.10
Output
$0.32
Cached input (read)
not listed
Context window
131,072 tokens
Maximum output
16,384 tokens
Accepts
text
Reasoning mode
no
Listed since
6 Dec 2024

No provider list price is recorded for this model: the figures above are what OpenRouter charges, which can differ from buying directly.

Collected from the OpenRouter models API (466 entries). 99 models are cross-checked against provider list prices in the LiteLLM price table.

About Llama 3.3 70B Instruct

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...

Description supplied by OpenRouter. Model id for the API: meta-llama/llama-3.3-70b-instruct

Other Meta models

Questions and answers

How much does Meta Llama 3.3 70B Instruct cost per million tokens?

At the collection of 3 Oct 2026, 08:40 UTC, OpenRouter listed Meta Llama 3.3 70B Instruct at $0.10 per million input tokens and $0.32 per million output tokens.

What would Meta Llama 3.3 70B Instruct cost per month?

For 1,000 requests a day with 3,000 input and 600 output tokens each, over a 30-day month and with no caching, the bill is $14.76. Change the numbers in the simulator on this page to match your own traffic.

Does Meta Llama 3.3 70B Instruct have a cheaper price for cached input?

The sources list no cache-read price for this model, so this site applies no caching discount to it.

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

131,072 tokens, with a maximum output of 16,384 tokens, as reported by OpenRouter.

Keep going