Is Llama 3 2 3b Instruct Fast available on other providers?

MetaLlama 3.2

Llama 3 2 3b Instruct Fast pricing

Llama 3 2 3b Instruct Fast appears on 1 price row here. Lowest input is $0.050 per million tokens from Zerogpu. Lowest output is $0.300 per million tokens from Zerogpu. Use the table and chart, then the calculator for your own volume.

131K context·1 provider·verified Oct 28, 2026

Estimate cost Compare with GPT-4o Pick any other model

Best input$0.050per 1M tokens · Zerogpu

Best output$0.300per 1M tokens · Zerogpu

Pricing across providers

Use this table to read Llama 3 2 3b Instruct Fast list prices. We show 1 source right now. Lowest input in the grid: Zerogpu. The chart below the table helps when output prices are much higher than input prices.

Zerogpu

Input / 1M

$0.050

Output / 1M

$0.300

Cached in: $0.025

Provider	Input / 1M	Output / 1M	Cached input	Batch
Z Zerogpu	$0.050	$0.300	$0.025	—

Input vs output · 1M tokens

Cost calculator

Use this block to stress test Llama 3 2 3b Instruct Fast cost without a spreadsheet. All estimates come from public list rates in this page.

In: $0.050/M·Out: $0.300/M·Cache: $0.025/M

Requests / day

Avg input tokens

0.005000¢ / req

Avg output tokens

0.015000¢ / req

Daily

$2.00

Monthly

$60

Annual

$730

Model specifications

These fields describe Llama 3 2 3b Instruct Fast as we store it (Family: Llama 3.2. source: Meta). They sit next to price so buyers can check limits and tools in one place.

Context window: 131,072 tokens
Max output: 8,192 tokens
Vision (images): No
Tool / function calling: No
Streaming: No
Released: N/A
Primary provider: Meta
Model family: Llama 3.2