LLM Open Weight

Llama 3.2 1B Instruct

by Meta

Prices last updated November 22, 2026

Meta's Llama 3.2 1B Instruct — smallest open-weight Llama 3.2 text model.

Context
131k
Providers
4
Cheapest Input
$0.005
Streaming Chat / Instruct

Price Comparison

Compare pricing across 4 providers serving Llama 3.2 1B Instruct

Provider Input $/1M Output $/1M Context Speed TTFT Status
DeepInfra
DeepInfra
$0.005 ● $0.010 131k — — Live
Novita AI
Novita AI
$0.020 $0.020 131k — — Live
Cloudflare Workers AI
Cloudflare Workers AI
$0.027 $0.201 — — — Live
OpenRouter
OpenRouter
$0.027 $0.201 60k — — Live
● Cheapest ● Fastest Prices in USD per 1M tokens

Benchmarks

Independent results for Llama 3.2 1B Instruct, as each source publishes them. Where a source tested several versions (effort levels, thinking modes, dated snapshots), the best one is shown and named under "As tested". Scores from different sources use different scales and aren't comparable with each other.

BenchmarkScoreRankAs tested
Reasoning
GPQA DiamondEpoch AI
Graduate-level multiple-choice questions in biology, physics and chemistry, written to be hard to look up.
23.9%±3.2
#226 of 232
Llama-3.2-1B-Instruct
Aug 2026
Math
Competition maths problems from the OTIS mock AIME exams (2024-2025).
0.6%±0.7
#210 of 215
Llama-3.2-1B-Instruct
Aug 2026
Coding
Text Arena votes on coding prompts only.
1,149±16
1,346 votes
#400 of 421
Llama 3.2 1B Instruct
Nov 2026
Chat
Text ArenaLMArena
Human votes on chat answers across all kinds of prompts (style-controlled).
1,111±8
8,045 votes
#408 of 426
Llama 3.2 1B Instruct
Nov 2026

Epoch AI: Epoch runs each benchmark itself on the models it evaluates, with the same harness for every model. The Epoch Capabilities Index combines many benchmarks into one score. Data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0).

LMArena: People compare two anonymous models side by side and vote for the better answer; ratings come from those votes (Bradley-Terry, style-controlled for text and vision). Data: LMArena (arena.ai) leaderboard dataset (CC BY 4.0).

Rank is among all models the source ranks, including ones we don't list.

Subscribe to our newsletter

News and updates, 1–2 emails per month. No spam.