Available Models
List of supported AI models and pricing
Available Models
Aize Platform provides access to multiple AI models through a unified API. All models use the OpenAI-compatible interface at https://api.aize.dev/v1.
Access to models depends on your subscription tier: FREE, PRO ($10/mo), MAX ($20/mo), ULTRA ($69/mo), or PAYG (wallet-based, no subscription). See the Plan Tiers & Model Access section below.
Model Aliases
We use model aliases that map to the actual underlying models. This allows us to:
- Seamless Updates: Update underlying models without breaking your code
- Consistent Naming: Use familiar model names across providers
- Easy Migration: Switch between providers transparently
Supported Models
Below is a list of currently supported models and their pricing per 1M tokens.
Pricing Details
Input vs Output Tokens
- Input Tokens: The tokens you send in your request (prompt)
- Output Tokens: The tokens generated in the response (completion)
Most models charge different rates for input and output tokens.
Token Calculation
Approximate token counts:
- 1 token ≈ 4 characters
- 1 token ≈ 0.75 words
- 100 tokens ≈ 75 words
Model Selection Guide
GPT-5.4 Family
| Variant | Best For |
|---|---|
| GPT-5.4 Nano | Fast, ultra-low-cost tasks; high-volume workloads |
| GPT-5.4 Mini | Balanced speed and intelligence; everyday use (default) |
| GPT-5.4 | Complex reasoning; code generation; multi-step problem solving |
| GPT-5.4 Pro | Not included in any plan — available via PAYG wallet only |
GPT-5.4 Mini is the recommended default for most use cases.
Claude Models
| Variant | Best For |
|---|---|
| Claude 4.5 Haiku | Fast, cost-efficient tasks; escalation from free tier |
| Claude 4.6 Sonnet | Detailed analysis; creative writing; nuanced conversations |
| Claude 4.8 Opus | Most demanding reasoning; enterprise-grade tasks |
Gemini Models
| Variant | Best For |
|---|---|
| Gemini 2.5 Flash | Fast multimodal tasks; real-time applications |
| Gemini 2.5 Pro | Advanced multimodal reasoning; long-context analysis |
| Gemini 3.1 Pro | Cutting-edge multimodal and long-document tasks |
GLM Models
| Variant | Best For |
|---|---|
| GLM-4.7 Flash | Ultra-fast responses; cost-sensitive high-volume workloads |
| GLM-5.1 | Balanced reasoning and speed |
| GLM-5 | Advanced reasoning; complex instruction following |
Other Notable Models
The following models are available via PAYG wallet but not included in any subscription plan:
- GPT-5.4 Pro
- Llama 3.3
- GPT-OSS 120B
Plan Tiers & Model Access
| Model | FREE | PRO | MAX | ULTRA |
|---|---|---|---|---|
| Auto | ✅ | ✅ | ✅ | ✅ |
| GPT-5.4 Nano | ✅ | ✅ | ✅ | ✅ |
| GLM-4.7 Flash | ✅ | ✅ | ✅ | ✅ |
| GPT-5.4 Mini | — | ✅ | ✅ | ✅ |
| Gemini 2.5 Flash | — | ✅ | ✅ | ✅ |
| GLM-5.1 | — | ✅ | ✅ | ✅ |
| Claude 4.5 Haiku | — | ✅ | ✅ | ✅ |
| GPT-5.4 | — | — | ✅ | ✅ |
| Claude 4.6 Sonnet | — | — | ✅ | ✅ |
| Gemini 2.5 Pro | — | — | ✅ | ✅ |
| Claude 4.8 Opus | — | — | — | ✅ |
| Gemini 3.1 Pro | — | — | — | ✅ |
| GLM-5 | — | — | — | ✅ |
Model Features
Context Windows
Different models support different context window sizes:
- GPT-5.4 family: 128K tokens
- Claude 4.5/4.6/4.8: 200K tokens
- Gemini 2.5/3.1: 1M tokens
- GLM family: 128K tokens
Function Calling
Most models support function calling (tools) for structured outputs. See the Quick Start for implementation details.
Vision Capabilities
Some models support image inputs. See the Quick Start for implementation details.
Image Generation Models
| Tier | Available Image Models |
|---|---|
| FREE | None |
| PRO | Qwen Image 2.0 |
| MAX | Qwen Image 2.0 Pro, GPT Image 1.5 (limited) |
| ULTRA | All image models + Qwen Image Edit Plus |