RouterLab
Back to the AI model catalog
openaiAvailableHigh availability

Hy4 Preview API

RouterLab publishes this openai model under the model ID hy4-preview. The facts below come from the active RouterLab catalog.

Model ID

hy4-preview

OpenAI-compatible API

Context window

960,000 tokens

Maximum output

64,000 tokens

Input / 1M tokens

$0.834

Output / 1M tokens

$2.501

Cache read / 1M tokens

$0.042

Cache write / 1M tokens

Same as input

Cache read reuses tokens already stored in the provider cache. Cache write creates or stores new cache tokens.

Catalog capabilities

  • Tool calling
  • Streaming
  • Structured output
  • Reasoning

Minimal API request

curl https://api.routerlab.ch/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"hy4-preview","messages":[{"role":"user","content":"Hello RouterLab"}]}'