Llama 3.1 405B Instruct
MetaOpen weights128K context
Lowest price, from Snowflake
Per million tokens
- Input
- $1.20
- Output
- $1.20
- Cached input
- —
- Batch input / output
- —
- Up to 16K output tokens per request.
Estimate your monthly cost
Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.
From Snowflake: $14.40 a month.
Where to buy it (5)
Sorted by your monthly estimate. Prices per million tokens.
SnowflakeCheapest
- Input / output
- $1.20 / $1.20
- Context
- 128K
- Per month
- $14.40
snowflake/llama3.1-405b
Amazon Bedrock
- Input / output
- $2.40 / $2.40
- Context
- 128K
- Per month
- $28.80
meta.llama3-1-405b-instruct-v1:0
Together AI
- Input / output
- $3.50 / $3.50
- Context
- 4K
- Per month
- $42.00
together_ai/meta-llama/Llama-3.1-405B-Instruct
Google Vertex AI
- Input / output
- $5.00 / $16.00
- Context
- 128K
- Per month
- $82.00
vertex_ai/meta/llama-3.1-405b-instruct-maas
Oracle Cloud
- Input / output
- $10.68 / $10.68
- Context
- 128K
- Per month
- $128.16
oci/meta.llama-3.1-405b-instruct
Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: Tool calling, Vision.