Models

Every model, one key

Every model Apigator can actually call — OpenRouter plus every provider we connect directly (AWS Bedrock, OpenAI, Gemini, Perplexity, Anthropic, Groq, Together, DeepInfra, Cerebras and more). Call any by the id shown. Prices (where published) are per 1M tokens in USD.

Loading models…

How to call

Each model lists the endpoint it uses (shown on its row). Pass the id as model with your Apigator key.

curl https://api.apigator.ai/v1/chat/completions \
  -H "Authorization: Bearer $APIGATOR_KEY" \
  -d '{"model":"openrouter/openai/gpt-4o","messages":[{"role":"user","content":"hi"}]}'

/v1/chat/completions — Chat

/v1/images/generations — Image gen

/v1/audio/speech — TTS

/v1/audio/transcriptions — Speech-to-text

/v1/embeddings — Embeddings

/v1/videos — Video gen (preview)

preview = video & music: the endpoint is live (OpenAI async job shape for video) but provider access is still being verified — see /api.md.

Full guide for agents: /api.md · Claude via the Claude Code CLI endpoint (allowlist-gated).