Flash — fastest and cheapest, lighter reasoningOpen Weights

Llama 3.2 3B Instruct Pricing

Meta · meta-llama-llama-3-2-3b-instruct

ShareX Facebook LinkedIn

Input / 1M tokens

$0.050

Output / 1M tokens

$0.330

Context window

131,072 tokens

≈ 175 pages of text

Max output

131,072 tokens

What it costs in practice

Typical request (1,200 in + 400 out tokens)$0.0002

1,000 requests / month$0.192/mo 10,000 requests / month$1.92/mo 100,000 requests / month$19.20/mo

Estimate your own workloadOpens the calculator with Llama 3.2 3B Instruct preloaded — adjust volume and token counts there.

Price history

List price per 1M tokens since we started tracking in Jun 2026. Each step marks a price change — hover a point for the exact date and rate.

What it excels at

Suitable for high-volume, low-cost text generation and basic instruction following where latency and throughput are priorities.

The business tradeoff

Limited reasoning depth and factual consistency compared with larger Llama variants; requires self-hosting with associated infrastructure and maintenance overhead.

Cheaper from Meta

Llama 3.2 1B InstructMeta$0.0001/ typical request

Same tier from other providers

GPT-5.4 NanoOpenAI$0.0007/ typical request Claude Haiku 4.5Anthropic$0.0032/ typical request Gemini 3.5 FlashGoogle$0.0054/ typical request

Head-to-head

Llama 3.2 3B Instruct vs GPT-5.4 Nano →Llama 3.2 3B Instruct vs Claude Haiku 4.5 →Llama 3.2 3B Instruct vs Gemini 3.5 Flash →

Vendor list rates, as of Jul 26, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.