OpenAI
openaiOpenAI's 3 models on ModelRunner span Image-to-Image, Speech-to-Text and Text-to-Image, from $0.145 per image upward.
3 public models — every one runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant over MCP.
OpenAI models & pricing
Whisper Large v3
openai
Transcribe or translate speech audio into text across 99 languages, with segment/word timestamps and optional speaker diarization.
GPT Image 2 Edit
openai
Edit an existing image from a text instruction, with precise instruction-following and accurate, legible in-image text, using up to 16 reference images and an optional mask.
GPT Image 2
openai
Generate images from a text prompt, with precise instruction-following (counts, layout, multi-part requests) and accurate, legible text rendered inside the image.
What you can build with OpenAI models
- Transcribe podcasts, meetings, and interviews to text Whisper Large v3
- Generate subtitles with timestamps for videos Whisper Large v3
- Translate foreign-language speech into English text Whisper Large v3
- Make precise text-instructed edits to product or marketing images GPT Image 2 Edit
- Add, remove, or replace objects in a photo by describing the change GPT Image 2 Edit
- Apply brand-accurate revisions to existing visuals GPT Image 2 Edit
- Generate images that follow precise instructions (counts, layout) GPT Image 2
- Create images with accurate embedded text GPT Image 2
Browse by capability
Call a OpenAI model in one request
Every endpoint shares the same lifecycle: submit to the queue, poll the status URL, fetch the result. Swap the endpoint to switch models — nothing else changes.
cURL
curl -X POST https://queue.modelrunner.run/openai/whisper \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "prompt": "..." }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }Use OpenAI models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every OpenAI model on this page as a tool — authorized via OAuth, results returned as hosted URLs in the conversation.
Claude Code
claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcpFrequently asked questions
What OpenAI models can I run on ModelRunner?
The catalog has 3 public OpenAI models: Whisper Large v3, GPT Image 2 Edit and GPT Image 2. They cover image-to-image, speech-to-text and text-to-image. Each one has its own page with a free playground, the full input schema, and copy-paste code.
How much do OpenAI models cost?
Pay-per-use, with no subscription: the 2 OpenAI models billed per image start at $0.145, and every page publishes its own rate — some are tiered, so a lower resolution or a shorter clip costs less per run. You buy credits and pay only for what you generate.
How do I call a OpenAI model from the API?
POST to https://queue.modelrunner.run/openai/whisper with an Authorization: Key header and the input fields as the top-level JSON body (no wrapper object), then poll the returned status_url and fetch the result from response_url. The JavaScript SDK (@modelrunner/client) wraps that in a single subscribe() call, which is the one place an { input } object is used.
Can I run OpenAI models from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and all 3 OpenAI models become tools your assistant can call with run_model — authorized over OAuth 2.1, so no API key goes into a config file. Results come back as hosted URLs in the conversation.
More on ModelRunner
Browse the full model catalog, compare live per-configuration rates on the pricing page, see curated sets on explore, or view every model creator.