Context Window
80,000
Input tokens
Full-context input ≈ $0.00
Model Cost Profile
Developer: meta-llama· Tokenizer: Llama3 · Instruct: llama3 · Quantization: unknown
Canonical ID: meta-llama/llama-3.2-3b-instruct
Pricing updated Apr 24, 2026
Live Pricing
Input: $0.0510
Output: $0.3400
Last synced Apr 24, 2026 · MMLU score via public benchmark data
Meta: Llama 3.2 3B Instruct is designed for applications requiring extensive context handling, featuring a context window of 131,072 tokens, making it suitable for complex dialogue systems and detailed content generation. With a competitive pricing structure of $0.02 per million tokens for both input and output, it offers cost-effective solutions for teams looking to scale their AI capabilities without breaking the budget. This model is particularly beneficial for businesses in sectors like customer support and content creation, where nuanced understanding and extensive context are crucial for delivering high-quality interactions.
Context Window
80,000
Input tokens
Full-context input ≈ $0.00
Max Output
—
Not specified
Input Price / 1M
$0.0510
Prompt tokens
Output Price / 1M
$0.3400
Completion tokens
Top Benchmark
34.7
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for Meta: Llama 3.2 3B Instruct. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.0510
Current Output / 1M
$0.3400
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.0510 |
| Output (Completion) | $0.3400 |
Estimate monthly spend for Meta: Llama 3.2 3B Instruct based on your workload.
Estimated Monthly Cost
$5.36
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.