replicate/meta/llama-2-7b

Best price — Output ($/1M tokens)

One row per access path (venue → underlying provider). Prices are each venue's published list price; performance is measured by Artificial Analysis. Your actual bill may vary by routing settings, fallbacks, region / ZDR, long-context tiers, and request features (JSON mode, tools, vision).

• #

  1

  Provider

  fireworks

  Class

  Direct host

  $ / 1M tokens

  Input $ / 1M tokens

  $0.2

  Output $ / 1M tokens

  $0.2

  Cache read $ / 1M tokens

  —

  -11.1% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —

• #

  2

  Provider

  replicate → meta

  Class

  Reseller

  $ / 1M tokens

  Input $ / 1M tokens

  $0.05

  Output $ / 1M tokens

  $0.25

  Cache read $ / 1M tokens

  —

  +11.1% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —