Skip to content

Anthropic Claude ​

Anthropic's Claude series, strong at coding, long-document understanding and agent tasks that need multi-step execution. It is the default model of Claude Code.

Choosing a group ​

GroupPrice
claudePay 23% of official price

All Claude models are in the claude group.

Prefer the native Claude Messages API, which gives full access to extended thinking, prompt caching, tool calls and other features. You can also call them through Chat Completions.

bash
curl https://api.codingrouter.ai/v1/messages \
  -H "x-api-key: $CODINGROUTER_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5-5",
    "max_tokens": 4096,
    "messages": [{"role": "user", "content": "Rewrite this function as an async version: ..."}]
  }'

Choosing a model ​

SeriesCharacteristics
OpusMost capable, for complex coding and long-running tasks
FableComplex reasoning and multi-step agent tasks
SonnetBalance of speed and capability, the first choice for everyday coding
HaikuFastest and cheapest, for high concurrency and simple tasks

Usage tips ​

  • Always set max_tokens; if you omit it, the gateway uses a default value.
  • Cache long system prompts or documents with cache_control. On repeated calls the input is billed at the cache price. See Prompt caching.
  • When extended thinking is on, max_tokens must be greater than budget_tokens.

Representative models ​

ModelGroupGood for
claude-opus-5-5claudeTop capability, complex coding and long tasks
claude-sonnet-5-5claudeFirst choice for everyday coding
claude-haiku-5-5claudeFast and low cost
claude-fable-5-2claudeComplex reasoning and agents

For the full list and prices see the model square.