Llama 2 70b

Provider: replicate · replicate/meta/llama-2-70b

Pricing per million tokens

Component USD per 1M tokens
Input $0.65
Output $2.75

Monthly cost estimates

Assuming 30% prompt-cache hit rate where available. Adjust for your actual usage.

Small
1M in / 200k out
$1.20
per month
Medium
10M in / 2000k out
$12.00
per month
Large
100M in / 20000k out
$120
per month

Context

Input window
4,096 tokens
Max output
4,096 tokens

Capabilities

  • ⬜ Vision (image input)
  • ⬜ Function / tool calling
  • ⬜ Prompt caching
  • ⬜ Web search
  • ⬜ JSON / response schema

Compare Llama 2 70b with similar models

Llama 2 70b Chat
replicate
$0.65 in / $2.75 out
Llama 3 70b
replicate
$0.65 in / $2.75 out
Llama 3 70b Instruct
replicate
$0.65 in / $2.75 out
Mixtral 8x7b Instruct V0.1
replicate
$0.30 in / $1.00 out
Gpt 5
replicate
$1.25 in / $10.00 out
Claude 4.5 Haiku
replicate
$1.00 in / $5.00 out

Pricing data sourced from LiteLLM and refreshed regularly. Last updated May 20, 2026. Always verify with the provider's official pricing page before making business decisions.