DataEyesAI
Official SiteConsoleDocs HomeGetting Started
Developer ToolsAI Models APITerms & Policies
Official SiteConsoleDocs HomeGetting Started
Developer ToolsAI Models APITerms & Policies
  1. Getting Started
  • Welcome to DataEyesAI
  • Quickstart
  • API Keys and Authentication
  • Base URL and SDKs
  • Models, Groups, and Pricing
  1. Getting Started

Models, Groups, and Pricing

This page explains how to choose a model in the Model Hub, read its pricing, and how groups and billing work.

Choose a model in the Model Hub#

Open the Model Hub in the console. You can filter by vendor, type, and tag. Click any model card to open its details:
SectionDescription
Model nameThe value for the model field. Use the copy button next to the name to avoid typos
Basic infoCapabilities, context length, input and output modalities
API endpointsProtocols and paths the model supports, for example openai: /v1/chat/completions or gemini: /v1beta/models/{model}:generateContent
Group pricingDiscount and unit price (USD) for each group
API tabSample calls for this model
TIP
Check "API endpoints" before you call a model. Image and video models usually support only their own dedicated APIs and cannot be called through /v1/chat/completions.

Billing types#

The Model Hub shows two billing types:
Billing typeApplies toPrice unit
Token billingText, multimodal understanding, and some image modelsUSD per million tokens, split into input, output, and Cache Read (some models also charge cache writes)
Per-request billingMost image, video, and music generation modelsUSD per call (or per image, per second)
Cost per request = tokens of each type × unit price × group discount. The actual charge is shown in Usage Logs.
NOTE
Only successful requests are billed. Requests that fail before reaching the model, such as authentication or parameter errors, are free.
If a streaming request disconnects midway, the tokens already generated are still billed.
Some models use tiered pricing for very long contexts; this is noted on the model detail page.

Groups#

A group determines which channels serve your requests and what price applies. The same model can cost different amounts in different groups.
The following groups are currently available:
GroupDescription
default (Official price)All models available at official prices
Brand groups (such as openai, claude-aws, gemini, deepseek, qwen)Discounted prices for that brand's models. See Group pricing on the model detail page for the exact discount
Choose a group type when you create a key:
Stability First / Price First: the system automatically picks among available groups following the auto-routing order shown on the model detail page. No manual choice needed.
Specify group: always use one group, useful when you want a fixed price.
Memberships and subscriptions
The Coding Plan page in the console offers subscription plans. After you subscribe, your account is upgraded to the plan's group for the plan period and gets lower prices; it returns to your original group when the plan expires. See the purchase page for each plan's credit, group, and duration.

Top-ups and balance#

Model credit: top up in Model Credit Top-up. All model calls are charged to this balance.
Search & Reader credit: purchase separately in MCP Products → MCP Plans & Top-up. It is not shared with your model balance.
Vouchers: view and use them in Voucher Management in the console.
Usage: Dashboard and Usage Logs in the console show spend by key, model, and time. You can also fetch it programmatically through the Balance and usage API.

Model catalog#

The following model families are available (see the Model Hub for the live list and prices):
CategoryFamilies
Text / multimodalOpenAI GPT, Anthropic Claude, Google Gemini, xAI Grok, DeepSeek, Qwen, Kimi, Zhipu GLM, MiniMax, ByteDance Seed, Doubao, Xiaomi MiMo, Tencent Hunyuan
ImageGPT Image, Gemini image (Nano Banana), Seedream, FLUX, Grok Imagine, Wan, Midjourney
VideoSeedance, Kling, Vidu, Wan, HappyHorse, MiniMax H3, Grok Imagine Video
EmbeddingsOpenAI text-embedding family
You can also call the List models API to get the models available to your current key.
Previous
Base URL and SDKs