Anthropic: Claude Sonnet 5Reasoning

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

  databricks

  Class

  Official

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $10

  Cache read $ / 1M tokens

  $0.2

  -0.0% vs consensus

  TTFT

  3.0s

  Throughput

  63.6 tps

  Uptime 24h

  —

  Requests 24h

  —

• #

  2

  Provider

  amazon-bedrock

  Class

  Official

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $10

  Cache read $ / 1M tokens

  $0.22

  +0.0% vs consensus

  TTFT

  197.9s

  reasoning 205.1s

  Throughput

  74.2 tps

  Uptime 24h

  —

  Requests 24h

  —

• #

  3

  Provider

  anthropic

  Class

  Official

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $10

  Cache read $ / 1M tokens

  $0.2

  +0.0% vs consensus

  TTFT

  1.6s

  reasoning 35.8s

  Throughput

  58.2 tps

  Uptime 24h

  —

  Requests 24h

  —

• #

  4

  Provider

  azure → azure-ai

  Class

  Official

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $10

  Cache read $ / 1M tokens

  $0.2

  +0.0% vs consensus

  TTFT

  171.9s

  reasoning 243.2s

  Throughput

  72.1 tps

  Uptime 24h

  —

  Requests 24h

  —

• #

  5

  Provider

  google

  Class

  Official

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $10

  Cache read $ / 1M tokens

  —

  +0.0% vs consensus

  TTFT

  189.7s

  reasoning 175.8s

  Throughput

  69.5 tps

  Uptime 24h

  —

  Requests 24h

  —

• #

  6

  Provider

  google-vertex

  Class

  Official

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $10

  Cache read $ / 1M tokens

  $0.2

  +0.0% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —

• #

  7

  Provider

  deepinfra → anthropic

  Class

  Reseller

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $10

  Cache read $ / 1M tokens

  —

  +0.0% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —

• #

  8

  Provider

  gmi

  Class

  Reseller

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $10

  Cache read $ / 1M tokens

  $0.2

  +0.0% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —

• #

  9

  Provider

  openrouter → amazon-bedrock

  Class

  Reseller

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $10

  Cache read $ / 1M tokens

  $0.2

  +0.0% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —

• #

  10

  Provider

  openrouter → anthropic

  Class

  Reseller

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $10

  Cache read $ / 1M tokens

  $0.2

  +0.0% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —

• #

  11

  Provider

  openrouter → azure

  Class

  Reseller

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $10

  Cache read $ / 1M tokens

  $0.2

  +0.0% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —

• #

  12

  Provider

  openrouter → claude-on-aws

  Class

  Reseller

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $10

  Cache read $ / 1M tokens

  $0.2

  +0.0% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —

• #

  13

  Provider

  openrouter → google-vertex

  Class

  Reseller

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $10

  Cache read $ / 1M tokens

  $0.2

  +0.0% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —

• #

  14

  Provider

  zeroeval → anthropic

  Class

  Reseller

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $10

  Cache read $ / 1M tokens

  —

  +0.0% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —

• #

  15

  Provider

  bedrock-converse

  Class

  Official

  $ / 1M tokens

  Input $ / 1M tokens

  $2.2

  Output $ / 1M tokens

  $11

  Cache read $ / 1M tokens

  $0.22

  +10.0% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —

• #

  16

  Provider

  bedrock

  Class

  Official

  $ / 1M tokens

  Input $ / 1M tokens

  $2.4

  Output $ / 1M tokens

  $12

  Cache read $ / 1M tokens

  $0.24

  +20.0% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —

• #

  17

  Provider

  lightningai

  Class

  Reseller

  $ / 1M tokens

  Input $ / 1M tokens

  $2

  Output $ / 1M tokens

  $15

  Cache read $ / 1M tokens

  —

  +50.0% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —

• #

  18

  Provider

  deepinfra

  Class

  Reseller

  $ / 1M tokens

  Input $ / 1M tokens

  $3

  Output $ / 1M tokens

  $15

  Cache read $ / 1M tokens

  —

  +50.0% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —

• #

  19

  Provider

  zeroeval → deepinfra

  Class

  Reseller

  $ / 1M tokens

  Input $ / 1M tokens

  $3

  Output $ / 1M tokens

  $15

  Cache read $ / 1M tokens

  —

  +50.0% vs consensus

  TTFT

  —

  Throughput

  —

  Uptime 24h

  —

  Requests 24h

  —