Llama 3.3 70B Versatile
Open Llama instruction model for multilingual chat, reasoning, and coding
Model facts
- Context window
- 131K tokens
- Maximum output
- 33K tokens
- Cheapest paid input
- $0.59 per 1M tokens
- Cheapest paid output
- $0.79 per 1M tokens
- Open weights
- yes
- Providers
- 2
Capabilities and modalities
tool calling, temperature control, open weights, text.
Observed price history
- 2026-08-24: $0.59 input / $0.79 output per 1M tokens
API providers
- Abacus — model id llama-3.3-70b-versatile; $0.59 input / $0.79 output per 1M tokens; provider documentation
- Helicone (Meta) — model id llama-3.3-70b-versatile; $0.59 input / $0.79 output per 1M tokens; provider documentation