llama-3.3-70b-instruct API pricing

Checked 12 Sept 2026 LLMs
$ per 1M input $0.100
$ per 1M output $0.320

Blended at 3:1 input to output: $0.155 per million tokens.

OpenRouter charges $0.100 per million input tokens and $0.320 per million output tokens. 2 of the models nearest it in price are cheaper on a blended basis.

$0.100
$/1M input
$0.320
$/1M output
131,072
Context window
$11.76
1k req/day, monthly

Against the models nearest in price

Blended at a 3:1 input to output ratio.

Calculator →
llama-3.3-70b-instruct against comparable models — checked 12 Sept 2026
Source
llama-3.3-70b-instruct This model OpenRouter $0.100 $0.320 131,072 $0.155

Last checked . Methodology

Questions

How much does llama-3.3-70b-instruct cost per million tokens?

$0.100 per million input tokens and $0.320 per million output tokens. At a 3:1 input to output mix that blends to $0.155. Checked 12 Sept 2026.

What would llama-3.3-70b-instruct cost for a real workload?

A thousand requests a day at 2,000 input and 600 output tokens each comes to $11.76 a month.

What is the context window for llama-3.3-70b-instruct?

131,072 tokens of input, with up to 16,384 tokens of output.

llama-4-scout · llama-4-scout-17b-16e-instruct · gpt-5-nano · gemini-2.0-flash · gemini-2.0-flash-001 · All OpenRouter models · Cost calculator