There are six main endpoints:
/v1/chat/completions.openai.base_url = 'https://api.airforce'['claude-3-haiku-20240307', 'claude-3-sonnet-20240229', 'claude-3-5-sonnet-20240620', 'claude-3-opus-20240229', 'chatgpt-4o-latest', 'gpt-4', 'gpt-4-0613', 'gpt-4-turbo', 'gpt-4o-mini-2024-07-18', 'gpt-4o-mini', 'gpt-3.5-turbo', 'gpt-3.5-turbo-0125', 'gpt-3.5-turbo-1106', 'gpt-3.5-turbo-16k', 'gpt-3.5-turbo-0613', 'gpt-3.5-turbo-16k-0613', 'gpt-4o', 'llama-3-70b-chat', 'llama-3-70b-chat-turbo', 'llama-3-8b-chat', 'llama-3-8b-chat-turbo', 'llama-3-70b-chat-lite', 'llama-3-8b-chat-lite', 'llama-2-70b-chat', 'llama-2-13b-chat', 'llama-2-7b-chat', 'llama-3.1-405b-turbo', 'llama-3.1-70b-turbo', 'llama-3.1-8b-turbo', 'LlamaGuard-2-8b', 'Yi-34B-Chat', 'Yi-34B', 'Yi-6B', 'Mixtral-8x7B-v0.1', 'Mixtral-8x22B', 'Mixtral-8x7B-Instruct-v0.1', 'Mixtral-8x22B-Instruct-v0.1', 'Mistral-7B-Instruct-v0.1', 'Mistral-7B-Instruct-v0.2', 'Mistral-7B-Instruct-v0.3', 'openchat-3.5', 'WizardLM-13B-V1.2', 'WizardCoder-Python-34B-V1.0', 'Qwen1.5-0.5B-Chat', 'Qwen1.5-1.8B-Chat', 'Qwen1.5-4B-Chat', 'Qwen1.5-7B-Chat', 'Qwen1.5-14B-Chat', 'Qwen1.5-72B-Chat', 'Qwen1.5-110B-Chat', 'Qwen2-72B-Instruct', 'gemma-2b-it', 'gemma-7b-it', 'gemma-2b', 'gemma-7b', 'dbrx-instruct', 'vicuna-7b-v1.5', 'vicuna-13b-v1.5', 'dolphin-2.5-mixtral-8x7b', 'deepseek-coder-33b-instruct', 'deepseek-coder-67b-instruct', 'deepseek-llm-67b-chat', 'Nous-Capybara-7B-V1p9', 'Nous-Hermes-2-Mixtral-8x7B-DPO', 'Nous-Hermes-2-Mixtral-8x7B-SFT', 'Nous-Hermes-llama-2-7b', 'Nous-Hermes-Llama2-13b', 'Nous-Hermes-2-Yi-34B', 'Mistral-7B-OpenOrca', 'alpaca-7b', 'OpenHermes-2-Mistral-7B', 'OpenHermes-2.5-Mistral-7B', 'WizardLM-2-8x22B', 'NexusRaven-V2-13B', 'Phind-CodeLlama-34B-v2', 'CodeLlama-7b-Python-hf', 'CodeLlama-7b-Python', 'CodeLlama-13b-Python-hf', 'CodeLlama-34b-Python-hf', 'CodeLlama-70b-Python-hf', 'snowflake-arctic-instruct', 'SOLAR-10.7B-Instruct-v1.0', 'StripedHyena-Hessian-7B', 'StripedHyena-Nous-7B', 'Llama-2-7B-32K-Instruct', 'CodeLlama-13b-Instruct', 'evo-1-131k-base', 'OLMo-7B-Instruct', 'Platypus2-70B-instruct', 'Snorkel-Mistral-PairRM-DPO', 'ReMM-SLERP-L2-13B', 'MythoMax-L2-13b', 'chronos-hermes-13b', 'Llama-Guard-7b', 'gemma-2-9b-it', 'gemma-2-27b-it', 'Toppy-M-7B', 'gemini-1.5-flash', 'gemini-1.5-pro', 'sparkdesk', 'cosmosrp']You can get a premium api key. Include the API key in the Authorization header as follows:
Authorization: Bearer YOUR_API_KEYYou can check the usage of your key via the following:
/check?key=<KEY>Get api key at https://discord.gg/pMeMK4FwXB
The /v1/chat/completions and /chat/completions endpoints are used to send a prompt to the specified LLM model and receive a response.
Send a POST request to /v1/chat/completions or /chat/completions with the following JSON payload:
{
'model': 'claude-3-opus',
'messages': [
{'role': 'system', 'content': 'System prompt (only the first message, once)'},
{'role': 'user', 'content': 'Message content'},
{'role': 'assistant', 'content': 'Assistant response'}
],
'max_tokens': 2048,
'stream': false,
'temperature': 0.7,
'top_p': 0.5,
'top_k': 0
}The response will be in the following format:
{
'id': 'chatcmpl-123',
'object': 'chat.completion',
'created': 1677652288,
'model': 'claude-3-opus',
'system_fingerprint': 'fp_44709d6fcb',
'choices': [{
'index': 0,
'message': {
'role': 'assistant',
'content': 'Response content'
},
'logprobs': null,
'finish_reason': 'stop'
}],
'usage': {
'prompt_tokens': 9,
'completion_tokens': 12,
'total_tokens': 21
}
}The /v1/models and /models endpoints are used to list all available models.
Send a GET request to /v1/models or /models to retrieve a list of available models.
The response will be in the following format:
{
'object': 'list',
'data': [
{
'id': 'model-id',
'object': 'model',
'created': 1686935002,
'owned_by': 'provider'
},
...
]
}The /v1/imagine and /imagine endpoints are used to generate images.
Send a GET request to /v1/imagine or /imagine with the following query parameters:
{
'prompt': 'A beautiful landscape',
'size': '1:1' [one of 1:1, 16:9, 9:16, 21:9, 9:21, 1:2 or 2:1]
'seed': 123456,
'model': 'flux' or 'flux-realism' or 'flux-anime' or 'flux-3d',
}The response will be an image in PNG format.
The response will be in the following format:
Content-Type: image/png
(binary image data)Example GET request:
GET /v1/imagine?prompt=A+beautiful+landscape&size=1:1&seed=123456&model=flux-realismThe /v1/imagine2 and /imagine2 endpoints are used to generate images fast and stable.
The /v1/ask and /ask endpoints are using the GlobalAsk api which performs a request to chatgpt with web search and image generation.
Send a GET request to /v1/ask or /ask with the following query parameter:
{
'prompt': 'What is ChatGPT'
}The response will be a text/event-stream consisting of multiple json chunks.
Every line is sent seperatly and contains a json code in the following format:
{
'message': STRING,
'url': STRING
}You can try the GlobalAsk API here.
The /v1/images/vision and /images/vision endpoints are used to describe an image using specified vision models.
Send a GET request to /v1/images/vision or /images/vision with the following query parameters:
{
'url': 'URL of the image to be described',
'model': 'gemini-pro-vision' // optional, default is 'gemini-pro-vision'
}Valid models: 'gpt-4o', 'gpt-4o-mini', 'gemini-pro-vision'
If no model is specified, the default model 'gemini-pro-vision' will be used.
The response will a string
Example GET request:
GET /v1/images/vision?url=https://example.com/image.png&model=gemini-pro-visionThe /v1/suno and /suno endpoints are used to generate a song using Suno's AI models.
There are two ways to interact with this endpoint:
To generate a song, send a POST request to /v1/suno or /suno with the following JSON payload:
{
"model": "chirp-v3-5", // Optional, can be one of "chirp-v2-xxl-alpha", "chirp-v3-5", "chirp-v3-0". Default is "chirp-v3-5".
"prompt": "Describe the type of song you want to generate.", // Required, between 1 and 200 characters.
"instrumental": "false", // Optional, if set to "true", generates an instrumental version.
"style": "genre or style", // Optional, between 1 and 120 characters. Only required for custom generation.
"custom": "false" // Optional, if set to "true", allows for longer and more detailed prompts (up to 1250 characters for most models, up to 3000 characters for "chirp-v3-5").
}To retrieve the status and URLs for an existing song, send a GET request to /v1/suno/<uuid> or /suno/<uuid> with the song's UUID.
Successful response will include:
{
"status": "success",
"clips": ["uuid1", "uuid2"]
}Each UUID can be used to retrieve the song's content via a subsequent GET request.
The response will include:
{
"status": "generating" | "finished",
"image_url": "https://link_to_image",
"audio_url": "https://link_to_audio",
"video_url": "https://link_to_video"
}POST /v1/suno
Content-Type: application/json
{
"model": "chirp-v3-5",
"prompt": "A catchy pop song with upbeat rhythm",
"instrumental": "false",
"custom": "false"
}GET /v1/suno/uuid1The /get-audio endpoint is used to convert text to speech and return the audio as an MP3 file. The text is provided via a URL query parameter.
Send a GET request to /get-audio with the following query parameter:
GET /get-audio?text=Your+text+here&voice=alexFor example, to convert "Hello world" to speech:
GET /get-audio?text=Hello+world&voice=sophiaAvailable voices are alex and sophia - more soon.
The response will be an MP3 audio file with the following format:
Content-Type: audio/mpeg
(binary audio data)Example GET request:
GET /get-audio?text=Hello+world&voice=alexSuccessful request will return an MP3 file containing the spoken text.
