> ## Documentation Index > Fetch the complete documentation index at: https://docs.deploy.com/llms.txt > Use this file to discover all available pages before exploring further. # Quickstart > From your first API key to your first API call, all within seconds. Making your first API call is easy—all you need is a Deploy API key and a model ID. # **Create Your API Key** Log in to Deploy and navigate to [Service API Keys](https://portal.deploy.com/?api_keys=1) in the sidebar. Click **Create API Key** to create a new Secret Key scoped to your organization. This key can be used with any "**Try Now >"** model. This Secret Key will only be visible upon generation. Copy and store it in a secure location. If you lose your Secret Key, you can generate a new one. *** # Install the OpenAI SDK If you're using Python, install the OpenAI Python SDK to make API requests to Deploy: ```python Python theme={null} pip install openai ``` Deploy supports the OpenAI-compatible API format, so you can use the OpenAI SDK with your Deploy API key and endpoint without needing a separate SDK. *** # **Make your first API call** Below is an example of a sample request. Replace the `api_key` callout with your Secret Key. You'll need to provide the model ID of your choice in `model` as well as a `base_url`, which is region-dependent (if you are a customer in `SF` or `VA`). * **Closest**: [https://api.deploy.com/api/v1](https://api.deploy.com/api/v1) * **SF**: [https://api-sf1.deploy.com/api/v1](https://api-sf1.deploy.com/api/v1) * **VA**: [https://api-va1.deploy.com/api/v1](https://api-va1.deploy.com/api/v1) If you're accessing from outside the US, you may have lower latency with: * **Closest**: [https://api-cdn.deploy.com/api/v1](https://api-cdn.deploy.com/api/v1) * **SF**: [https://api-sf1-cdn.deploy.com/api/v1](https://api-sf1-cdn.deploy.com/api/v1) * **VA**: [https://api-va1-cdn.deploy.com/api/v1](https://api-va1-cdn.deploy.com/api/v1) The example below uses the model `deepseek-ai/deepseek-v4.1-flash-1017`. ```python Python (OpenAI SDK) wrap theme={null} from openai import OpenAI client = OpenAI( base_url="https://api.deploy.com/api/v1", api_key="DEPLOY_API_KEY", ) response = client.chat.completions.create( model="deepseek-ai/deepseek-v4.1-flash-1017", messages=[{"role": "user", "content": "Explain TCP and UDP in two sentences."}], ) print(response.choices[0].message.content) ``` ```bash cURL wrap theme={null} curl https://api.deploy.com/api/v1/chat/completions \ -H "Authorization: Bearer $DEPLOY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek-ai/deepseek-v4.1-flash-1017", "messages": [{"role": "user", "content": "Hello!"}] }' ``` Your response will be similar to the following example: ```json theme={null} { "id": "bf7eb425-c8ee-11f1-bc46-67542ee84316", "object": "chat.completion", "created": 1792106317, "model": "deepseek-ai/deepseek-v4.1-flash-1017", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "Hello! How can I help you today?", "reasoning_content": "The user just said \"Hello!\" That's a simple greeting. I should respond warmly and openly, inviting them to share what they need. No need for tools or complex analysis here—just a friendly, natural reply that sets a helpful tone. I'll keep it simple and engaging." }, "finish_reason": "stop", "logprobs": null } ], "usage": { "prompt_tokens": 32, "completion_tokens": 68, "total_tokens": 100, "prompt_tokens_details": { "cached_tokens": 0 }, "completion_tokens_details": { "reasoning_tokens": 58 } } } ``` And that's it—you've made your first API call. *** # Submit images and videos You can send visual inputs to models that support image or video understanding. You can provide media using a URL or a Base64-encoded data URI. The media is included in the message content alongside your text prompt. Supported media types and formats vary per model—check the **Input Modality** column in [Available Models](https://docs.deploy.com/models-and-pricing.md#available-open-source-models). ## Image ```python Python (Image) wrap theme={null} from openai import OpenAI client = OpenAI( base_url="https://api.deploy.com/api/v1", api_key="DEPLOY_API_KEY", ) response = client.chat.completions.create( model="deepseek-ai/deepseek-v4.1-flash-1017", messages=[ { "role": "user", "content": [ { "type": "text", "text": "Describe this image.", }, { "type": "image_url", "image_url": { "url": "https://example.com/image.jpg", }, }, ], } ], ) print(response.choices[0].message.content) ``` ```bash cURL wrap theme={null} curl -X POST "https://api.deploy.com/api/v1/chat/completions" \ -H "Authorization: Bearer $DEPLOY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek-ai/deepseek-v4.1-flash-1017", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image." }, { "type": "image_url", "image_url": { "url": "https://example.com/image.jpg" } } ] } ] }' ``` ## Video ```python Python wrap theme={null} from openai import OpenAI client = OpenAI( base_url="https://api.deploy.com/api/v1", api_key="DEPLOY_API_KEY", ) response = client.chat.completions.create( model="zai-org/glm-5.3-flash", messages=[ { "role": "user", "content": [ { "type": "text", "text": "Summarize what happens in this video.", }, { "type": "video_url", "video_url": { "url": "https://example.com/video.mp4", }, }, ], } ], ) print(response.choices[0].message.content) ``` ```bash cURL wrap theme={null} curl -X POST "https://api.deploy.com/api/v1/chat/completions" \ -H "Authorization: Bearer $DEPLOY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "zai-org/glm-5.3-flash", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Summarize what happens in this video." }, { "type": "video_url", "video_url": { "url": "https://example.com/video.mp4" } } ] } ] }' ``` ## Base64 Useful when the media is stored locally or when you don't want to provide an externally hosted URL. ```python Python (Image) wrap theme={null} from openai import OpenAI import base64 import mimetypes client = OpenAI( api_key="DEPLOY_API_KEY", base_url="https://api.deploy.com/api/v1", ) image_path = "image.jpg" mime_type, _ = mimetypes.guess_type(image_path) if mime_type is None: mime_type = "image/jpeg" with open(image_path, "rb") as image_file: encoded_image = base64.b64encode(image_file.read()).decode("utf-8") data_url = f"data:{mime_type};base64,{encoded_image}" response = client.chat.completions.create( model="deepseek-ai/deepseek-v4.1-flash-1017", messages=[ { "role": "user", "content": [ { "type": "text", "text": "Describe this image.", }, { "type": "image_url", "image_url": {"url": data_url}, }, ], } ], ) print(response.choices[0].message.content) ``` ```python Python (Video) wrap theme={null} import base64 import mimetypes from openai import OpenAI client = OpenAI( api_key="DEPLOY_API_KEY", base_url="https://api.deploy.com/api/v1", ) video_path = "video.mp4" mime_type, _ = mimetypes.guess_type(video_path) if mime_type is None: mime_type = "video/mp4" with open(video_path, "rb") as video_file: encoded_video = base64.b64encode(video_file.read()).decode("utf-8") data_url = f"data:{mime_type};base64,{encoded_video}" response = client.chat.completions.create( model="zai-org/glm-5.3-flash", messages=[ { "role": "user", "content": [ { "type": "text", "text": "Summarize what happens in this video.", }, { "type": "video_url", "video_url": { "url": data_url, }, }, ], } ], ) print(response.choices[0].message.content) ``` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.