llama-3.3-70b-instruct
Llama-3.3-70B-Instruct
Made by Meta. Sold by 4 providers, from $0.10 per million input tokens.
- Maker
- Meta
- Released
- 2024-12-06
- Context
- 131K tokens
- Max output
- 131K tokens
- Input
- text
- Output
- text
- Open weights
- Yes
- Knowledge cutoff
- 2024-12
Where to buy it
| Provider | Input $/M | Output $/M | Blended* | Holds your prompt | Training |
|---|---|---|---|---|---|
| DeepInfra turbo | $0.10 | $0.32 | $0.16 | runs it 🇺🇸 United States | no training |
| Microsoft Azure | $0.71 | $0.71 | $0.71 | runs it 🇺🇸 United States | no training |
| Amazon Bedrock IN-REGION US | $0.72 | $0.72 | $0.72 | runs it 🇺🇸 United States | no training |
| OVHcloud | ≈$0.75 €0.67 | ≈$0.75 €0.67 | ≈$0.75 | runs it 🇫🇷 France | no training |
≈ converted from EUR at 1 EUR = $1.1193 (ECB reference rate, 2026-10-23)
Blended is our calculation: (3 × input + output) ÷ 4, US dollars per million tokens — most calls read far more than they write. Tiers that are cheaper because they train on your data are not used for the “from” price.
Retirement dates
| Provider | Id on that provider | Shuts down | Source |
|---|---|---|---|
| Microsoft Azure | Llama-3.3-70B-Instruct | 2027-01-31 | provider page |