Llama 3.3 70B API Pricing
Open-weight · 128K context · Available from 7 hosts. Cheapest: Meta at $0.13 input / $0.4 output per 1M tokens.
Among Meta's 10 open-weight models tracked here, Llama 3.3 70B ($0.71/$0.71 per 1M tokens) is above Llama 3.1 70B ($0.2/$0.6) and below Llama 4 Maverick ($0.35/$1.15).
Llama 3.3 70B price by host (7 providers)
| Host | Input /1M | Output /1M | In+Out |
|---|---|---|---|
| Meta | $0.13 | $0.4 | $0.53 |
| Novita | $0.16 | $0.48 | $0.64 |
| DeepInfra | $0.17 | $0.51 | $0.68 |
| Groq | $0.19 | $0.57 | $0.76 |
| Together | $0.2 | $0.6 | $0.8 |
| OpenRouter | $0.2 | $0.6 | $0.8 |
| Fireworks | $0.21 | $0.63 | $0.84 |
Prices per 1M tokens, USD. Snapshot 2026-07 — verify with the provider before relying on them.
Llama 3.3 70B cost calculator
Frequently asked
Llama 3.3 70B costs $0.13 per 1M input tokens and $0.4 per 1M output tokens at its cheapest host (Meta).
Llama 3.3 70B supports a context window of about 128K tokens. Remember every token in the context is billed on each call.
Across 7 hosts, Meta is currently cheapest at $0.13/$0.4 per 1M tokens, versus Fireworks at $0.21/$0.63. Prices change often — use the comparison table above.