Appndo
All models

Llama 2 70B Chat

Meta4K context

LMArena score 1115 · #357 overall · #371 in coding (2026-10-13)

Official price from Perplexity

Per million tokens

Input
$0.70
Output
$2.80
Cached input
—
Batch input / output
—
  • Up to 4K 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 Perplexity: $12.60 a month. Replicate is the cheapest seller at $12.00, $0.60 less.

Where to buy it (2)

Sorted by your monthly estimate. Prices per million tokens.

  • ReplicateCheapest

    Input / output
    $0.65 / $2.75
    Context
    4K
    Per month
    $12.00

    replicate/meta/llama-2-70b-chat

  • PerplexityOfficial

    Input / output
    $0.70 / $2.80
    Context
    4K
    Per month
    $12.60

    perplexity/llama-2-70b-chat

Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: —.

Similar models