Meta Llama 3.3 70B Instruct: price rise input $0.100 → $0.590 per 1M tokens (+490 %), output $0.320 → $0.790 per 1M tokens (+147 %)

On the listed price of Meta Llama 3.3 70B Instruct changed: input $0.100 → $0.590 per 1M tokens (+490 %); output $0.320 → $0.790 per 1M tokens (+147 %). A later check on confirmed it. Prices as listed in the United States.

What changed

Meta Llama 3.3 70B Instruct is more expensive on OpenRouter. Source: price page as read.

What it does to a task

Standard tasks, visible output only, no cache discount; month = 20 tasks an hour around the clock.

Price change: Published input and output rates before and now; both money axes start at zero. Published rates · Llama 3.3 70B Instruct The same token volumes are priced before and after the confirmed rate change. Published rates · USD per million tokens. Open circle: before. Filled circle: now.
Price change.Published rates · Llama 3.3 70B Instruct The same token volumes are priced before and after the confirmed rate change. Published rates · USD per million tokens. Open circle: before. Filled circle: now. Open image · Explore the chart · Measured Lab · CC BY 4.0
TaskPer task, beforePer task, nowPer month, beforePer month, now
L1 · Micro-task (classification or strict JSON extraction)$0.0002$0.0010$3.12$15.23
L2 · Deep analysis over a 50,000-token document$0.017$0.096$246.16$1,404.23
L3 · Agentic coding loop, 15 steps$0.134$0.783$1,962.68$11,435.52

Same task on other models

The L2 task on other models we follow closely, at today's prices:

Recalculate for your workload

Open the task cost calculator with this model and your own numbers. Model card with the full price history

Explore the numbers

Published rates · Llama 3.3 70B Instruct

What the price change does to your bill

The same token volumes are priced before and after the confirmed rate change.

Input / 1M tokens$0.10 → $0.59$0.00$0.20$0.40$0.60$0.80Output / 1M tokens$0.32 → $0.79$0.00$0.20$0.40$0.60$0.80Input / 1M tokens$0.10 → $0.59$0.00$0.20$0.40$0.60$0.80Output / 1M tokens$0.32 → $0.79$0.00$0.20$0.40$0.60$0.80

Published rates · USD per million tokens. Open circle: before. Filled circle: now.

Before$246.16Now$1,404.23$0$500$1,000$1,500Before$246.16Now$1,404.23$0$500$1,000$1,500
Fresh inputVisible output

159,000 input + 3,000 visible output tokens per task. No cache discount; hidden reasoning excluded.

$1,158.07 more per month at 14,600 tasks.

Before$3.12Now$15.23$0$5$10$15$20Before$3.12Now$15.23$0$5$10$15$20
Fresh inputVisible output

1,500 input + 200 visible output tokens per task. No cache discount; hidden reasoning excluded.

$12.10 more per month at 14,600 tasks.

Before$1,962.68Now$11,435.52$0$5,000$10,000$15,000Before$1,962.68Now$11,435.52$0$5,000$10,000$15,000
Fresh inputVisible output

1,315,500 input + 9,000 visible output tokens per task. No cache discount; hidden reasoning excluded.

$9,472.85 more per month at 14,600 tasks.

Assumption: 20 tasks/hour × 730 hours. No cache discount; hidden reasoning excluded.

Read the price change briefing · Model and full price history

Confirmed price change

First seen and confirmed are different dates.

  1. Before
  2. First seen
  3. Confirmed
Published rate / 1MBeforeNow
Input$0.10$0.59
Output$0.32$0.79

A second measurement on a later date confirmed each new rate. The dates describe our readings, not a provider announcement date.

Sources: this page; published model prices (data (JSON)); task assumptions (data (JSON)). Published prices · Observed responses · Calculated scenarios · Assumptions stated with each chart.