Autoregressive framework on the Janus Pro 7B model that unifies multimodal understanding and image generation in one architecture.
DeepSeekImage GenerationProprietary EndpointAutoregressive framework on the Janus Pro 7B model that unifies multimodal understanding and image generation in one architecture.
janus-pro-deepseekPOST /v1/images/generationsPOST /v1/chat/completionsPOST /v1/images/analysisLive pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
Janus-Pro DeepSeek serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id janus-pro-deepseek. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "janus-pro-deepseek",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.empiriolabs.ai/v1",
api_key="YOUR_EMPIRIOLABS_API_KEY",
)
response = client.chat.completions.create(
model="janus-pro-deepseek",
messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)Request parameters supported by the Janus-Pro DeepSeek API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| prompt | string | - | - | Text description for image generation. |
| generation_image_size | enum | square | square, square_hd, portrait_4_3, portrait_16_9, landscape_4_3... | Output image dimensions (e.g. 384x384, 768x768). |
| generation_temperature | number | 1 | 0.1 to 2 | Sampling temperature for image generation. Higher = more variation. |
| generation_cfg_weight | number | 5 | 1 to 20 | Classifier-free guidance weight. Higher = closer to prompt but less creative. |
| generation_num_images | number | 1 | 1 to 4 | How many images to generate (1-4). |
| generation_seed | number | - | - | Random seed for reproducibility. Same seed + prompt = same output. |
| image_url | string | - | - | URL of an image to analyze (image-understanding mode). |
| question | string | - | - | Question to answer about the supplied image. |
| analysis_temperature | number | 0.1 | 0 to 1 | Sampling temperature for image analysis. Higher = more variation. |
| analysis_top_p | number | 0.95 | 0.1 to 1 | Nucleus sampling probability mass for image analysis. |
| analysis_seed | number | - | - | Random seed for analysis output reproducibility. |
Image generation and image analysis both billed per image.
On EmpirioLabs, Janus-Pro DeepSeek is billed pay as you go: Image Generation $0.030 per image; Image Analysis $0.030 per uploaded image. The live rate card on this page always matches what the API charges.
Yes. Janus-Pro DeepSeek serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to janus-pro-deepseek.
Yes. The EmpirioLabs playground runs Janus-Pro DeepSeek in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Explore our models, or contact us about business inquiries, custom deployments, or anything else.
