All modelsCalculate what your real prompts cost on Llama 3.3 70B Instruct
Llama 3.3 70B Instruct
open sourceMeta model, released 6 Dec 2024.
$0.22
per 1M input tokens
$0.5
per 1M output tokens
$0.11
per 1M cached-read tokens
Price history
input $/1M output $/1M7 Jul 2026 → 5 Oct 2026
Specifications
- Lab
- Meta
- Released
- 6 Dec 2024
- Context window
- 131k tokens
- Max output
- 16k tokens
- Input modalities
- text
- Output modalities
- text
- Knowledge cutoff
- 2023-12-31
- Open source
- Yes
Benchmarks
| Benchmark | Category | Score | As of |
|---|---|---|---|
| LMArena (Chatbot Arena) | coding | 1268.6 (1262.1–1275.2) | 13 Sept 2026 |
| LMArena (Chatbot Arena) | overall | 1274 (1270.5–1277.5) | 13 Sept 2026 |
LMArena (Chatbot Arena) data © their authors, CC-BY-4.0
Frequently asked questions
How much does Llama 3.3 70B Instruct cost?
Llama 3.3 70B Instruct costs $0.22 per 1M input tokens and $0.5 per 1M output tokens (list price, updated every 6 hours).
What is Llama 3.3 70B Instruct's context window?
Llama 3.3 70B Instruct supports a 131k-token context window with up to 16k output tokens.