Pass IndexThe State of AISign in

Llama 3.2 1B Instruct

The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out).

text → text · made by Meta

$0.005$0.01per Mtok in / out
DeepInfra · 11 sellers

Sold by 13 ways

SellerLaneRate
AWS Bedrock cloudstandard$0.1per Mtok in$0.1per Mtok outaws.amazon.com · read 2026-08-24
AWS Bedrock cloudin-region$0.1per Mtok in$0.1per Mtok outpricing.us-east-1.amazonaws.com · read 2026-08-24
IBM watsonx cloudstandard$0.1per Mtok in$0.1per Mtok outraw.githubusercontent.com · read 2026-09-16
IBM watsonx.ai cloudstandard$0.1per Mtok in$0.1per Mtok outraw.githubusercontent.com · read 2026-08-28
DeepInfra aggregatorstandard$0.005per Mtok in$0.01per Mtok outapi.deepinfra.com · read 2026-08-25
ElectronHub aggregatorstandard$0.01per Mtok in$0.02per Mtok outapi.electronhub.ai · read 2026-09-16
Novita AI aggregatorstandard$0.02per Mtok in$0.02per Mtok outapi.novita.ai · read 2026-08-25
Cloudflare aggregatorstandard$0.027per Mtok in$0.2per Mtok outdevelopers.cloudflare.com · read 2026-08-25
Cloudflare aggregatornot on the seller's list todaysandbox$0.027per Mtok in$0.2per Mtok outdevelopers.cloudflare.com · read 2026-08-25
Inference.net aggregatorstandard$0.027per Mtok in$0.2per Mtok outapi.inference.net · read 2026-09-16
OpenRouter aggregatorstandard$0.027per Mtok in$0.2per Mtok outopenrouter.ai · read 2026-08-24
SambaNova Cloud aggregatorstandard$0.04per Mtok in$0.08per Mtok outraw.githubusercontent.com · read 2026-09-16
Together AI aggregatorstandard$0.06per Mtok in$0.06per Mtok outraw.githubusercontent.com · read 2026-09-16

Measured 5 standings

PlaceBoardMetricScore
35thof 36Balrog — Epoch AIAverage progress0.066
203rdof 222Chess puzzles — Epoch AImean_score0
285thof 290OTIS Mock AIME 2024-2025mean_score0.556
306thof 313GPQA Diamondmean_score23.927
635thof 656Epoch capabilities index — Epoch AIECI Score102.43

About

Llama 3.2 1B Instruct — a text model from Meta, sold by 11 companies from $0.005 in and $0.01 out per million tokens, placed 203rd of 222 on Chess puzzles — Epoch AI.

It takes text and returns text, with a context window of 131,072 tokens. It was published in August 2024, trained on material up to December 2023. The catalogue files it under reasoning. Eleven companies sell it. The cheapest is $0.005 in and $0.01 out per million tokens at DeepInfra. Beside the standard rate there is a regional lane. It has been measured on 5 boards, and stands best at 203rd of 222 on Chess puzzles — Epoch AI.

Every current figure

Maker
Meta
Register
model
Takes
text
Returns
text
Context
131,072 tokens
Published
August 2024
Knowledge to
December 2023
Parameters
1.2 billion
Licence
not read
Sellers
11
Maker's own price
not read
Price
$0.005 in and $0.01 out per million tokens — DeepInfra
Boards
5
Best place
203rd of 222 — Chess puzzles — Epoch AI

Known as 4 names

Llama 3.2 1Bmeta.llama3-2-1b-instruct-v1:0@cf/meta/llama-3.2-1b-instructmeta-llama/Llama-3.2-1B-Instruct