- Lowest · DeepInfra
- $0.03 / $0.06
- per 1M in / out
As of Nov 11, 2026, Meta Llama 3 8B Instruct costs $0.03 per million input tokens and $0.06 per million output tokens from DeepInfra. The cheapest of 3 providers is DeepInfra at $0.03 / $0.06. No price change since Appndo started tracking it on Oct 14, 2026. Recent price changes
Providers (3)
Sorted by your monthly estimate. Prices per million tokens. DeepInfra also lists up to 8K output tokens per request.
DeepInfraCheapest
- Input / output
- $0.03 / $0.06
- Context
- 8K
- Per month
- $0.42
deepinfra/meta-llama/Meta-Llama-3-8B-Instruct
- Input / output
- $0.05 / $0.25
- Context
- —
- Per month
- $1.00
replicate/meta/meta-llama-3-8b
- Input / output
- $0.05 / $0.25
- Context
- —
- Per month
- $1.00
replicate/meta/meta-llama-3-8b-instruct
- Input / output
- $0.15 / $0.15
- Context
- 8K
- Per month
- $1.80
anyscale/meta-llama/Meta-Llama-3-8B-Instruct
Cloud and hosted providers may add regional pricing, minimums or platform fees. Supports: Tool calling.
Similar models
Common questions
How much does the Meta Llama 3 8B Instruct API cost?
As of Nov 11, 2026, Meta Llama 3 8B Instruct costs $0.03 per million input tokens and $0.06 per million output tokens from DeepInfra.
Where is Meta Llama 3 8B Instruct cheapest?
As of Nov 11, 2026, the cheapest of 3 providers is DeepInfra at $0.03 per million input tokens and $0.06 per million output tokens. Appndo lists no official price from Meta.
What is the context length of Meta Llama 3 8B Instruct?
Meta Llama 3 8B Instruct takes up to 8K tokens of context at DeepInfra.
How does Meta Llama 3 8B Instruct compare with similar models?
Meta Llama 3 8B Instruct has no LMArena score yet. Other Meta models and their cheapest price per million input / output tokens: Llama 3.3 70B Instruct ($0.12 / $0.30), Llama 4 Maverick 17B 128e Instruct FP8 ($0.05 / $0.10), and Llama 4 Scout 17B 16e Instruct ($0.05 / $0.10).