Llama 3.2 3B API Pricing
Open-weight · 128K context · Available from 7 hosts. Cheapest: Novita at $0.048 input / $0.048 output per 1M tokens.
Among Meta's 10 open-weight models tracked here, Llama 3.2 3B ($0.06/$0.06 per 1M tokens) is above Llama 3.2 1B ($0.04/$0.04) and below Llama 3.1 8B ($0.05/$0.08).
Llama 3.2 3B price by host (7 providers)
| Host | Input /1M | Output /1M | In+Out |
|---|---|---|---|
| Novita | $0.048 | $0.048 | $0.096 |
| DeepInfra | $0.051 | $0.051 | $0.102 |
| Groq | $0.057 | $0.057 | $0.114 |
| Meta | $0.06 | $0.06 | $0.12 |
| Together | $0.06 | $0.06 | $0.12 |
| OpenRouter | $0.06 | $0.06 | $0.12 |
| Fireworks | $0.063 | $0.063 | $0.126 |
Prices per 1M tokens, USD. Snapshot 2026-07 — verify with the provider before relying on them.
Llama 3.2 3B cost calculator
Frequently asked
Llama 3.2 3B costs $0.048 per 1M input tokens and $0.048 per 1M output tokens at its cheapest host (Novita).
Llama 3.2 3B supports a context window of about 128K tokens. Remember every token in the context is billed on each call.
Across 7 hosts, Novita is currently cheapest at $0.048/$0.048 per 1M tokens, versus Fireworks at $0.063/$0.063. Prices change often — use the comparison table above.