Meta models on Amazon Bedrock
7 Meta models available through Bedrock, with price per 1M tokens, context window and region coverage.
| Model | Context | Input | Output | Regions |
|---|---|---|---|---|
| Llama 3 70B Instruct meta.llama3-70b-instruct-v1:0 | 8K | $2.65 | $3.50 | On-demand 5 Inference profile only 0 |
| Llama 3 8B Instruct meta.llama3-8b-instruct-v1:0 | 8K | $0.300 | $0.600 | On-demand 5 Inference profile only 0 |
| Llama 3.1 70B Instruct meta.llama3-1-70b-instruct-v1:0 | 128K | $0.720 | $0.720 | On-demand 1 Inference profile only 2 |
| Llama 3.1 8B Instruct meta.llama3-1-8b-instruct-v1:0 | 128K | $0.220 | $0.220 | On-demand 1 Inference profile only 2 |
| Llama 3.3 70B Instruct meta.llama3-3-70b-instruct-v1:0 | 128K | $0.720 | $0.720 | On-demand 1 Inference profile only 2 |
| Llama 4 Maverick 17B Instruct meta.llama4-maverick-17b-instruct-v1:0 | — | $0.240 | $0.970 | On-demand 0 Inference profile only 3 |
| Llama 4 Scout 17B Instruct meta.llama4-scout-17b-instruct-v1:0 | — | $0.170 | $0.660 | On-demand 0 Inference profile only 3 |
Common questions
- Which Meta model is cheapest on Amazon Bedrock?
- Llama 4 Scout 17B Instruct at $0.170 per 1M input tokens in us-east-1, against $0.660 per 1M output tokens.
- Which Meta model is available in the most AWS regions?
- Llama 3 70B Instruct, callable in 5 of the 16 regions tracked here — 5 on-demand and 0 through a cross-region inference profile.
- Which Meta model has the largest context window on Bedrock?
- Llama 3.1 70B Instruct, with a 128K-token context window.