AI & compute
Inference, generation and sandboxed execution priced per call: chat tiers, image generation, text-to-speech, speech-to-text, and code execution in an isolated sandbox.
LLM inference
POST /api/llmLLM inference proxy - send an OpenAI-format chat/completions request and get a response from GPT-4o-mini. Supports visio…
try in playground →LLM inference (Pro)
POST /api/llm-proLLM inference proxy (Pro tier) - GPT-4o or GPT-4.1. Supports vision (up to 2 image URLs) and structured output (response…
try in playground →LLM inference (Premium)
POST /api/llm-premiumLLM inference proxy (Premium tier) - o3 or o3-mini reasoning models. Supports vision (up to 2 image URLs) and structured…
try in playground →Image generation
POST /api/image-genGenerate an image from a text prompt using GPT Image 2 (low quality, 1024x1024). No API key needed; pay per call via x40…
try in playground →Image generation (HD)
POST /api/image-gen-hdGenerate a higher-quality image from a text prompt using GPT Image 2 (medium quality, 1024x1024). No API key needed; pay…
try in playground →Image generation (Premium)
POST /api/image-gen-premiumGenerate a larger image from a text prompt using GPT Image 2 (medium quality): 1536x1024 landscape by default, 1024x1536…
try in playground →Code execution
POST /api/code-runExecute Python or JavaScript code in a secure, isolated cloud sandbox. Returns stdout, stderr, and the expression result…
try in playground →Code execution (Pro)
POST /api/code-run-proExecute Python or JavaScript code in a secure, isolated cloud sandbox (Pro tier). Same as /api/code-run but with 60s tim…
try in playground →Text-to-speech (lite)
POST /api/tts-liteConvert text to speech with Kokoro-82M, a fraction of the price of /api/tts. Returns base64-encoded mp3 or pcm. The same…
try in playground →Text-to-speech
POST /api/ttsConvert text to speech with ElevenLabs Eleven v4 Turbo: returns audio (the base64-encoded file in the format asked for: …
try in playground →Text-to-speech (HD)
POST /api/tts-hdConvert text to speech with ElevenLabs Eleven v4, its most expressive model (inline audio tags such as [whispering] are …
try in playground →Speech-to-text
POST /api/transcribeTranscribe audio to text using OpenAI (gpt-transcribe). Provide a URL to an audio file (mp3, wav, m4a, etc.) and get bac…
try in playground →Speech-to-text (Pro)
POST /api/transcribe-proTranscribe audio to text using OpenAI (gpt-transcribe) - the same model as /api/transcribe with a longer cap. Provide a …
try in playground →Speech-to-text (OpenAI transcription wire)
POST /v1/audio/transcriptionsOpenAI's own transcription wire: POST multipart/form-data with a `file` part and get the transcript back. Point any Whis…
try in playground →Speech-to-text, long audio (OpenAI transcription wire)
POST /v1/pro/audio/transcriptionsOpenAI's transcription wire on the ten-minute tier: POST multipart/form-data with a `file` part. Same model as /v1/audio…
try in playground →Text embeddings
POST /api/embedGenerate a text embedding vector using OpenAI text-embedding-3-small (1536 dimensions). Ideal for semantic search, RAG, …
try in playground →Text embeddings (Large)
POST /api/embed-largeGenerate a text embedding vector using OpenAI text-embedding-3-large (3072 dimensions). Higher accuracy than the small m…
try in playground →Content moderation
POST /api/moderateCheck text for harmful content using OpenAI moderation (omni-moderation-latest). Returns flagged status, category breakd…
try in playground →Typed judgment
POST /v1/judgeAsk a typed question about any content and get an answer your code can branch on, not prose to parse. Send state (the co…
try in playground →Decisions (OpenAI wire)
POST /v1/decisionsOpenAI's Decisions API on its own wire: point an OpenAI SDK's base URL here and client.decisions.create works unchanged,…
try in playground →