A curated collection of 21 AI APIs with ready-to-use Requestly collections for instant testing.
Skip the API documentation hunt. This repo provides:
- 21 AI APIs - Curated and ready to test. More coming soon!
- Provider-level Collections - All APIs from a single provider (e.g., OpenAI) are grouped together in one file.
- Git-Controlled - Seamlessly manage collections with standard Git commands.
- Pre-configured Variables - Just add your API keys, and the requests are ready to go.
- Working Examples - Real requests that you can send immediately.
***
-
Clone the Repository
- Open your terminal and run the following command to clone the repo:
git clone https://github.com/Ronakkadhi/awesome-ai-apis.git
- Open your terminal and run the following command to clone the repo:
-
Set Up Requestly Workspace
- Open the Requestly Desktop App.
- Go to "Workspaces" and create a new Local Workspace.
- Select the
awesome-ai-apisfolder you just cloned. Requestly will automatically read and load all the collections.
-
Add Your API Keys
- Go to the "Variables" section within any imported collection.
- Add your API key (e.g.,
OPENAI_API_KEY). - Keys are stored locally and are never shared.
-
Start Testing
- Select any API request and click Send.
- Modify parameters as needed to test different AI services instantly.
| Name | Provider | Type | Docs / Website |
|---|---|---|---|
| OpenAI (Chat Completions) | OpenAI | Text/Chat LLM | Docs |
| OpenAI Images (DALL·E) | OpenAI | Image Generation | Docs |
| OpenAI Audio (Speech-to-Text) | OpenAI | Speech-to-Text | Docs |
| OpenAI Audio (Text-to-Speech) | OpenAI | Text-to-Speech | Docs |
| OpenAI (GPT-3.5 family) | OpenAI | Multimodal Chat | Docs |
| OpenAI Image Edits | OpenAI | Image Edit | Docs |
| OpenAI Image Variations | OpenAI | Image Variation | Docs |
| Anthropic (Claude Messages) | Anthropic | Text/Chat LLM | Docs |
| Google Gemini - Text generation | Gemini | Multimodal LLM | Docs |
| Google Gemini (Vision) | Gemini | Multimodal Chat | Docs |
| Google Gemini - Speech generation | Gemini | Multimodal LLM | Docs |
| OpenRouter (Router over many LLMs) | OpenRouter | Aggregator | Docs |
| OpenAI GPT oss 120b | OpenRouter | Text Generation | Docs |
| OpenAI GPT oss 20b | OpenRouter | Text Generation | Docs |
| Groq (OpenAI-compatible) | Groq | Text/Chat LLM | Docs |
| Meta-llama/Llama-3.1-8B-Instruct | Groq | Text/Chat LLM | Docs |
| Mistral (Coming soon) | Mistral | Text/Chat LLM | Docs |
| ElevenLabs V3 (Coming soon) | ElevenLabs | Text-to-Speech | Docs |
| AssemblyAI Summarize (Coming soon) | AssemblyAI | Summary from audio | Docs |
| AssemblyAI (STT)(Coming soon) | AssemblyAI | Speech-to-Text | Docs |
- Most APIs work immediately with just API keys, but some may require additional setup.
- File upload APIs might require specific content-type adjustments.
- Beta/newer APIs may have changed since collection creation.
- Always refer to official documentation for the most up-to-date requirements.
- Found a great AI API we missed? Want to add more examples?
- Fork this repo.
- Add the new API to an existing or new provider JSON file.
- Add any new variables needed.
- Update the README table.
- Submit a PR.
- Each new API should include: Proper authentication headers, variables, and body
Made with ❤️ for the developer community