Language models
Claude, GPT, and Gemini families for chat, coding, reasoning, and tool use — the same LLM coverage a Requesty user expects.
Requesty is an LLM-only proxy aimed at Claude Code. RunAPI is multi-modal — 130+ models spanning text, image, video, music, and audio — with an MCP server, a CLI, SDKs for JavaScript, Go, and Ruby, and the same OpenAI-compatible API at 50% off official rates.
Both are OpenAI-compatible gateways that route requests to multiple model providers. Requesty focuses on LLM text routing for coding tools. RunAPI covers the same LLM use cases and adds image, video, music, and audio generation plus a developer toolkit.
Both expose an OpenAI-compatible API and route Claude, GPT, and Gemini for tools like Claude Code and Cursor.
Requesty is LLM-only. RunAPI adds image, video, music, and audio generation under one key.
RunAPI ships an MCP server, a CLI, and SDKs for JavaScript, Go, and Ruby, plus a prompt library.
RunAPI bills pay-as-you-go at 50% of official model rates, with no subscription.
The table compares the two gateways across the features developers evaluate when choosing a proxy: modality coverage, model count, tooling, and API compatibility.
| Feature | Requesty | RunAPI |
|---|---|---|
| LLM routing | Yes | Yes |
| Image generation | No | Yes |
| Video generation | No | Yes |
| Music and audio | No | Yes |
| Total models | LLM models | 130+ across all modalities |
| MCP server | No | Yes |
| Official SDKs | OpenAI-compatible only | JavaScript, Go, Ruby + OpenAI-compatible |
| OpenAI-compatible API | Yes | Yes |
Requesty routes language models. RunAPI routes language models and generative media models under a single key, so one integration covers text, images, video, music, and audio.
Claude, GPT, and Gemini families for chat, coding, reasoning, and tool use — the same LLM coverage a Requesty user expects.
Text-to-image and image-edit models for generation, inpainting, and style transfer, callable from the same API.
Text-to-video and image-to-video models for short clips and animation, billed pay-as-you-go.
Music generation and audio models for soundtracks, voiceovers, and effects — modalities Requesty does not cover.
Beyond the raw API, RunAPI ships tooling that an LLM-only proxy typically lacks: a Model Context Protocol server, a command-line tool, and language SDKs.
Discover models, check pricing, create tasks, and poll results directly from MCP-aware hosts like Claude Code and Cursor.
Run generation tasks and manage keys from the terminal without writing code.
Typed clients for JavaScript, Go, and Ruby, alongside full OpenAI-SDK compatibility for every other language.
A searchable catalog of reusable prompt examples across image, video, and audio modalities.
RunAPI bills pay-as-you-go at 50% of each provider's official rate, with no subscription tier required. The table shows representative flagship LLM rates; image, video, and audio are priced per task.
| Model | Official input /M | Official output /M | RunAPI input /M | RunAPI output /M |
|---|---|---|---|---|
| Claude Sonnet 4.6 | $6.00 | $30.00 | $3.00 | $15.00 |
| Claude Opus 4.7 | $10.00 | $50.00 | $5.00 | $25.00 |
| GPT-5.4 | $2.50 | $15.00 | $1.25 | $7.50 |
| Gemini 2.5 Pro | $1.25 | $10.00 | $0.63 | $5.00 |
RunAPI applies a 50% discount across all providers. Media models are billed per task. Prices verified June 2026.
Sign up at runapi.ai. The free tier requires no credit card.
Go to Dashboard → API Keys, create a key, and save it.
Change your client's base URL to https://api.runapi.ai/v1 and use the RunAPI key. Your existing OpenAI-compatible code stays the same.
Call image, video, or audio models through the same key, or use the MCP server and CLI for non-code workflows.
Yes for LLM routing. Both are OpenAI-compatible, so switching usually means changing the base URL and key in your existing client. RunAPI then adds image, video, music, and audio models that Requesty does not offer, under the same account.
RunAPI covers generative media — image, video, music, and audio — alongside the LLM routing both gateways share. It also ships an MCP server, a command-line tool, and official SDKs for JavaScript, Go, and Ruby, plus a searchable prompt library.
RunAPI exposes more than 130 models across every modality: language models from the Claude, GPT, and Gemini families, plus image, video, music, and audio generation models. All of them are reachable through one key and one OpenAI-compatible API, so a single integration covers both text routing and generative media without separate accounts.
Yes. Like Requesty, RunAPI works with Claude Code and Cursor by overriding the base URL in each tool's settings. Set the Anthropic or OpenAI base URL to RunAPI and use your key. Both tools then run without further modification, and the same key also unlocks image, video, and audio models Requesty does not offer.
RunAPI bills at 50% of each provider's official published rate, with no subscription required. Sonnet 4.6 runs $3 input and $15 output per million tokens, and GPT-5.4 runs $1.25 input and $7.50 output, for example. Image, video, music, and audio models are billed per task at the same half-off positioning.
No. If your code already uses an OpenAI-compatible client with Requesty, migrating means pointing the base URL at api.runapi.ai/v1 and swapping in your RunAPI key. The request and response shapes stay identical, so your application logic does not change. You can migrate gradually and run both gateways side by side during the transition.
Both. RunAPI publishes typed SDKs for JavaScript, Go, and Ruby, and remains fully compatible with the OpenAI SDK for every other language. It also ships an MCP server and a command-line tool for workflows outside a code editor, plus a searchable prompt library — tooling an LLM-only proxy like Requesty typically does not include.
Create a free RunAPI account for 130+ models across text, image, video, and audio — OpenAI-compatible, at 50% off official rates.