Llama 3.2 1B Instruct

Provider: Meta Llama US

Scheduled for retirement on 2026-11-20.
Input price
$0.027
/ 1M tokens
Output price
$0.20
/ 1M tokens
Context
60K tokens
Max output 54K tokens

Overview

Meta's Llama 3.2 1B Instruct is a 1-billion parameter budget model built for basic natural language tasks like summarization and dialogue.

Strengths

  • Input cost of $0.027 per million tokens
  • Output cost of $0.201 per million tokens
  • Supports 60,000 token context window
  • Handles 54,000 maximum output tokens

Best use cases

  • High-volume text summarization pipelines
  • Basic multilingual dialogue systems
  • Lightweight NLP preprocessing tasks

Pricing position

Slightly cheaper input than GPT-5 Nano at $0.025/M, but features a smaller 60k context window versus the 400k in GPT-5 Nano.

Caveats

Knowledge cutoff is December 2023 and scheduled retirement is November 2026. Llama 3.1 8B offers lower output pricing at $0.08/M.

Notes drafted by an LLM from the figures on this page (2026-11-12) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
54K tokens
Knowledge cutoff
2023-12-31
Listed on OpenRouter
2024-09-25
Tracked since
2026-05-08
Last updated
2026-11-10

Features

No information available

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.01
1M (small app) 1 0.5 $0.13
10M (mid scale) 10 5 $1.28
100M (large) 100 50 $12.75

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Meta Llama

Similar-priced models

Source: OpenRouter API (meta-llama/llama-3.2-1b-instruct)