Models

The text API follows the OpenAI Chat Completions shape. Point an OpenAI-compatible client to the OmevAI base URL and keep the key on your server.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://llmapi.omev.be/v1",
    api_key=os.environ["OMEV_API_KEY"],
)

response = client.chat.completions.create(
    model="omev-lite",
    messages=[{"role": "user", "content": "Summarise this page in five bullets: ..."}],
    max_tokens=500,
)

print(response.choices[0].message.content)

Text models and prices

Prices per 1 million tokens. Both models work on every key.

Model	Recommended use	Input	Cached input	Output
omev-lite	High-volume, clearly specified text work such as extraction, data organisation, short rewriting and structured output	$0.15	$0.015	$1.25
omev-pro	Complex instructions, planning, long-form drafting and work that needs deeper reasoning	$0.625	$0.0625	$5.00
omev-pro, input above 200,000 tokens	The same model for very long prompts	$1.25	$0.125	$7.50

Output includes reasoning tokens. Cached input is the repeated beginning of a prompt the service has recently seen and costs 10% of the input price. When the input of one request is longer than 200,000 tokens, the whole request is billed at the long-context row.

Image and video models

Model	What it makes	Price	Availability
omev-image-jobs	Asynchronous 1K-class images for automated pipelines, optional reference images	$0.021 / $0.024 / $0.039 per image (low / medium / high)	On request
omev-image-lite	One or more inline 1024x1024 images	$0.0192 per image	On request
omev-image-main	One inline 1K-class image, up to 1536x1024 or 1024x1536	$0.021 per image	On request
omev-image-pro	One or more inline 1K-class images with reliable text in the picture	$0.024 per image ($0.1968 at medium quality)	On request
omev-video-lite	Simple video scenes, 4–12 s, 768p	$0.039 per second	On request
omev-video	People, complex motion and camera movement, 4–15 s, 720p or 1080p	$0.069 / $0.135 per second	On request
omev-video-premium	Premium video up to 30 s, 720p or 1080p, reference images	from $0.075 / $0.15 per second	On request

See Image generation, Video generation and Models and prices for every product and price.

GET /v1/models returns the documented products enabled for the key. Do not build an integration around an unfamiliar or internal name.

Choosing between omev-lite and omev-pro

Start with omev-lite when the instruction and output are clear. Use omev-pro when the difficulty is reasoning: several dependent constraints, planning, long context or a response that must keep a complex argument consistent.

Moving to omev-pro does not replace a clear prompt. State the goal, required facts, audience, language, format and constraints in the request.

Text endpoint

• POST /v1/chat/completions
• streaming with "stream": true
• structured JSON with response_format
• standard system, user and assistant messages

Validate JSON against your own schema before storing or publishing it. When you set max_tokens explicitly, it caps the output tokens billed to your account. OmevAI's internal generation floors and hidden reasoning budgets remain unchanged, but they cannot raise billed output above max_tokens. Also set a client timeout that matches your use case.

Image and video endpoints

Image and video instructions are available to everyone; the products are switched on for a key on request through support@omev.be. See Image generation and Video generation for the request shapes.

Stable public surface

Build against the public omev-* name, documented route and documented fields. The underlying technical model, provider, internal attempts and OmevAI's own cost are not part of the client response and may change without requiring an integration change.