Model

Llama 3.2 1B Instruct

6 providers · 6 listingsreleased Jan 1, 2025

$0.01

lowest input /M · Inference

$0.01

lowest output /M · Inference

131K

context window

60K

max output

Compare providers (sorted by listed input price)

5 of 6 providers publish a price for Llama 3.2 1B Instruct. The cheapest full-context option is Pioneer at $0.1/$0.201 per M. Inference lists lower but caps context at 16K.

			Cache read /M	Cache write /M		Capabilities
Inference meta/llama-3.2-1b-instruct	$0.01	$0.01	—	—	16K	no reasoningtoolsno structuredno vision	Jan 1, 2025
Kilo Gateway meta-llama/llama-3.2-1b-instruct	$0.027	$0.201	—	—	60K	no reasoningno toolsno structuredno vision	Sep 25, 2024
OpenRouter meta-llama/llama-3.2-1b-instruct	$0.027	$0.201	—	—	60K	no reasoningno toolsno structuredno vision	Sep 25, 2024
Cloudflare Workers AI @cf/meta/llama-3.2-1b-instruct	$0.027	$0.201	—	—	60K	no reasoningno toolsno structuredno vision	Sep 25, 2024
Pioneer meta-llama/Llama-3.2-1B-Instruct	$0.1	$0.201	$0.1	$0.1	131K	reasoningno toolsno structuredno vision	Sep 25, 2024
Nvidia meta/llama-3.2-1b-instruct	—	—	—	—	128K	no reasoningtoolsstructuredno vision	Sep 18, 2024

Best price history

Daily lowest published price across live providers. A lower line is better for the buyer.

Best input /M: $0.01unchanged
Best output /M: $0.01unchanged
Provider coverage: 6; 7 at the start · 24 snapshots

Published best prices are unchanged.

24 daily snapshots collected from Aug 21, 2026 through Sep 14, 2026. A price chart will appear after the first real move.

Price badge

![Llama 3.2 1B Instruct price](https://www.vaanalytics.in/badge/llama321binstruct.svg)

https://www.vaanalytics.in/badge/llama321binstruct.svg

Live SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.

Recent changes

Changelog →

contextvia openrouter · Aug 25, 2026
- output: 60K → 54K tokens
contextvia kilo · Aug 25, 2026
- output: 60K → 54K tokens

Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.