Skip to content
NINJA

Llama 3.3 70B Instruct

Released by Meta on 6 Dec 2024.

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

Input price
$0.71 / 1M tokens
Output price
$0.71 / 1M tokens
Context window
131K tokens
Longest reply
115K tokens

About this model

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 from the model’s public catalogue listing.

Capabilities

Reads
Text
Writes
Text
Reasoning mode
No
Tool calling
Yes
Open weights
Yes
Cached input
$0.71 / 1M tokens

What it would cost

At list price, without caching or batch discounts.

1,000 chat replies2K tokens in, 500 out each
$1.77
Summarise 100 long reports50K tokens in, 1K out each
$3.62
A coding agent’s working day20M tokens in, 1M out
$14.91
Price your own workload on every model

Price history

Per 1M tokens, input then output. Tracked since 30 Sept 2026.

10 Nov 2026
$0.59 → $0.71+20%$0.79 → $0.71-10%
5 Nov 2026
$0.20 → $0.59+195%$0.52 → $0.79+52%
5 Nov 2026
$0.10 → $0.20+100%$0.32 → $0.52+63%
4 Nov 2026
$0.20 → $0.10-50%$0.52 → $0.32-38%
3 Nov 2026
$0.10 → $0.20+100%$0.32 → $0.52+63%
3 Nov 2026
$0.20 → $0.10-50%$0.52 → $0.32-38%
3 Nov 2026
$0.10 → $0.20+100%$0.32 → $0.52+63%
16 Oct 2026
$0.59 → $0.10-83%$0.79 → $0.32-59%
13 Oct 2026
$0.22 → $0.59+168%$0.50 → $0.79+58%
9 Oct 2026
$0.10 → $0.22+120%$0.32 → $0.50+56%
8 Oct 2026
$0.22 → $0.10-55%$0.50 → $0.32-36%
5 Oct 2026
$0.10 → $0.22+120%$0.32 → $0.50+56%
5 Oct 2026
$0.22 → $0.10-55%$0.50 → $0.32-36%
4 Oct 2026
$0.10 → $0.22+120%$0.32 → $0.50+56%

Alternatives at a similar price

From other labs, priced within about 40% of Llama 3.3 70B Instruct, with a comparable context window.

More from Meta

See all