Llama 3.3 70B Instruct
Popular open Llama workhorse for multilingual chat, coding, and self-hosting
Model facts
- Context window
- 131K tokens
- Maximum output
- 12K tokens
- Cheapest paid input
- $0.135 per 1M tokens
- Cheapest paid output
- $0.4 per 1M tokens
- Open weights
- yes
- Providers
- 2
Capabilities and modalities
tool calling, temperature control, open weights, text.
Local hardware estimate
At 4K context: Q4_K_M 44.2 GiB, Q8_0 77.0 GiB, F16 138.6 GiB working memory.
- Parameters
- 70.6 billion
- Architecture
- llama
- Model license
- llama3.3
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Observed price history
- 2026-08-24: $0.13 input / $0.4 output per 1M tokens
- 2026-09-01: $0.135 input / $0.4 output per 1M tokens
API providers
- LLM Gateway (NovitaAI) — model id novita/llama-3.3-70b-instruct; $0.135 input / $0.4 output per 1M tokens; provider documentation
- LLM Gateway (Cerebras) — model id cerebras/llama-3.3-70b-instruct; $0.85 input / $1.2 output per 1M tokens; provider documentation