Anthropic: Claude Sonnet 5 (batch)

Anthropic

anthropic/claude-sonnet-5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

Context

1M

Input /1M

$1.00

Output /1M

$5.00

Latency (TTFT)

1,705ms

Pricing

Per 1M tokens, in USD

Input$1.00

Output$5.00

Cache read$0.10

Cache write (5m)$1.25

Cache write (1h)$2.00

Specs

text inimage infile intext outModerated

TokenizerClaude

Max output tokens128,000

Supported parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstool_choicetoolsverbosity

Where it ranks on price

Against 157 routable models

Input$1.00

Cheaper than 35% of routable models

Output$5.00

Cheaper than 28% of routable models

Benchmarks

Intelligence38.4

Coding71.5

Agentic44.3

Composite scores (0–100) from Artificial Analysis, via OpenRouter's model catalog.

Call this model

Swap in your Mizan key — the request/response bodies are OpenAI chat-completion shaped.

cURL

curl https://api.app-mizan.com/v1/chat/completions \
  -H "Authorization: Bearer mizan_rt_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'

Models

Anthropic: Claude Sonnet 5 (batch)

Anthropic

anthropic/claude-sonnet-5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

Context

1M

Input /1M

$1.00

Output /1M

$5.00

Latency (TTFT)

1,705ms

Pricing

Per 1M tokens, in USD

Input$1.00

Output$5.00

Cache read$0.10

Cache write (5m)$1.25

Cache write (1h)$2.00

Specs

text inimage infile intext outModerated

TokenizerClaude

Max output tokens128,000

Supported parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstool_choicetoolsverbosity

Where it ranks on price

Against 157 routable models

Input$1.00

Cheaper than 35% of routable models

Output$5.00

Cheaper than 28% of routable models

Benchmarks

Intelligence38.4

Coding71.5

Agentic44.3

Composite scores (0–100) from Artificial Analysis, via OpenRouter's model catalog.

Call this model

Swap in your Mizan key — the request/response bodies are OpenAI chat-completion shaped.

cURL

curl https://api.app-mizan.com/v1/chat/completions \
  -H "Authorization: Bearer mizan_rt_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'