AI API playground

Send a live request to any chat, image, video or audio model in the catalog, tune the parameters, and copy the matching OpenAI-compatible code.

API playground

Compose, run, and inspect one real API request.

Select a model, adjust its supported parameters, then compare the output with the exact JSON body and cURL command your app will send.

134

Modèles

Providers

Modes

Key required to run

Live runs use the public /v1 API and are reflected in usage, billing, and async job history.

zenmux$1.00 / 1M input tokens · $5.00 / 1M output tokensAvailable

claude-haiku-4-5

Fastest and cheapest Claude. Within ~5 percentage points of Sonnet 4.5 on many benchmarks at roughly one-third the cost.

MessageRequiredStreamingResponse formatTemperatureTop pMax tokens

Contract parameters

stoptoolstool_choiceuser

/v1/chat/completions

Live output appears here after a successful request.

Request preview

{
  "model": "claude-haiku-4-5",
  "messages": [
    {
      "role": "user",
      "content": ""
    }
  ],
  "stream": true
}

Model catalog snapshot134 models across 13 providers.