Input
What is sent to the model: agent instructions, conversation, documents, and tool results.
AI at SEION
What it costs to use artificial intelligence at SEION, how each usage is calculated, and the rules behind pricing.
How usage is measured
Language models charge by tokens, small pieces of text (one token is roughly four characters, or about three-quarters of a word). Each model call has:
What is sent to the model: agent instructions, conversation, documents, and tool results.
The part of the input the model received recently (fixed agent instructions or conversation history). It is usually charged at 10% of the input price.
What the model generates: its answer and internal reasoning. It is the most expensive component and usually weighs most in the bill.
Input categories are mutually exclusive: each token is charged only once, at its applicable rate.
Agents, assistants, automations
Prices per million tokens.
| Model | Best for | Input | Cached | Output | Tier |
|---|---|---|---|---|---|
| gpt-6-astra | Complex reasoning, programming, demanding professional work | 20.00 | 2.00 | 100.00 | €€€€ |
| gpt-6.1-sol | High capability, balancing intelligence and cost | 4.00 | 0.40 | 20.00 | €€€ |
| gpt-6-luna | Efficient for focused tasks, automation, and high volume | 0.20 | 0.02 | 1.00 | € |
| Model | Best for | Input | Cached | Output | Tier |
|---|---|---|---|---|---|
| gpt-5.6-sol | Complex professional work, agents, advanced reasoning | 8.00 | 0.80 | 40.00 | €€€ |
| gpt-5.6-terra | Balanced intelligence, speed, and cost | 4.00 | 0.40 | 24.00 | €€€ |
| gpt-5.6-luna | Low cost, high speed, high volume | 0.40 | 0.04 | 2.40 | €€ |
| Model | Best for | Input | Cached | Output | Tier |
|---|---|---|---|---|---|
| gpt-5.5 | Larger context and agent capabilities | 10.00 | 1.00 | 60.00 | €€€€ |
| gpt-5.4 | Maximum context and performance for advanced agents | 5.00 | 0.50 | 30.00 | €€€ |
| gpt-5.3 | Advanced reasoning and complex tasks | 3.50 | 0.35 | 28.00 | €€€ |
| gpt-5.2 | Complex analysis and deep reasoning | 3.50 | 0.35 | 28.00 | €€€ |
| gpt-5.1 | Business automation and assistants | 2.50 | 0.25 | 20.00 | €€€ |
| gpt-5-mini | Fast, low-cost chat and repetitive tasks | 0.50 | 0.05 | 4.00 | €€ |
| gpt-5-nano | Simple tasks and high volume | 0.10 | 0.01 | 0.80 | € |
| Model | Best for | Input | Cached | Output | Tier |
|---|---|---|---|---|---|
| gpt-4o | Versatile multimodal: support, creativity, visual analysis | 5.00 | 2.50 | 20.00 | €€€ |
| gpt-4o-mini | Affordable lightweight automation and basic support | 0.30 | 0.15 | 1.20 | € |
GPT-4o cached input is 50% of input pricing; for other models, 10%.
Images
| Model | Input (text and source images) | Cached input | Output (generated image) |
|---|---|---|---|
| gpt-image-2 | 8.00 | 2.00 | 30.00 |
Note: Prices per million tokens. Input uses the image rate because source images make up most of the input when editing or composing.
| Quality | 1024×1024 | 1024×1536 / 1536×1024 |
|---|---|---|
| Low | 0.008 | 0.012 |
| Medium | 0.032 | 0.047 |
| High | 0.125 | 0.187 |
Approximate amounts per image; actual cost depends on the tokens generated.
Models without individual pricing
If usage comes from a model without its own price, the generic rate applies (per million tokens):
Note: A model is charged at its own rate or the generic rate, never another model’s rate.
For every AI call
Use the model’s price; if unavailable, the agent’s configured model price; otherwise, the default.
Separate input, cached input, and output.
Every text call counts at least 8 input tokens.
Calculate each component; the total is their sum.
If the model has no cached-input rate, cached tokens are not charged.
Each usage record stores its tokens, itemized cost, and applied rate. Later price changes do not affect historical usage.
Example
10,000 input tokens (6,000 cached) and 800 response tokens.
With gpt-6-luna it would cost 0.0017; with gpt-6-astra, 0.1720.
| Item | Tokens | Rate / 1M | Cost |
|---|---|---|---|
| Input | 4,000 | 4.00 | 0.0160 |
| Cached input | 6,000 | 0.40 | 0.0024 |
| Output | 800 | 24.00 | 0.0192 |
| Total | 0.0376 |
Model catalog
In SEION’s model catalog, each model displays a tier from 1 to 4 for quick comparison:
Set a maximum spend for each agent, combining selected usage periods (today, this month, by contact, etc.) and optionally applying a condition. Once exceeded, the agent stops responding and actions can be triggered, such as notifying someone.
Each agent shows its spend and tokens for today, the current month, and the previous month. The AI usage log details every call.