Model List
Anyone currently supports the following AI models, all accessible through a unified OpenAI-compatible API.
Prices are for reference only. Check the Model Marketplace in your dashboard for real-time pricing. Unit: USD / million tokens.
OpenAI
| Model | Input | Output | Context | Features |
|---|
gpt-5.4 | $0.10 | $0.60 | 1M | Flagship model, reasoning/code/creative |
gpt-5.3-codex | $0.08 | $0.64 | 1M | Code specialist, programming/debug/refactor |
Anthropic Claude
| Model | Input | Output | Context | Features |
|---|
claude-opus-4-6 | $1.00 | $5.00 | 1M | Most powerful reasoning, complex analysis |
claude-opus-4-6-fast | $20.00 | $100.00 | 1M | Opus fast variant, lower latency |
claude-sonnet-4-6 | $0.45 | $2.25 | 1M | Balanced performance and price, daily driver |
Google Gemini
| Model | Input | Output | Context | Features |
|---|
gemini-3.1-pro-preview | $1.20 | $9.00 | 1M | Multimodal + long context, great value |
DeepSeek
| Model | Input | Output | Context | Features |
|---|
DeepSeek-V3.2 | $0.10 | $0.15 | 128K | Best value, strong Chinese capability |
Zhipu GLM
| Model | Input | Output | Context | Features |
|---|
GLM-5.1 | $1.00 | $3.00 | 128K | Chinese LLM, excellent comprehension |
xAI Grok
| Model | Input | Output | Context | Features |
|---|
grok-4.20 | $1.20 | $4.00 | 256K | Real-time info + reasoning, X/Twitter integrated |
MiniMax
| Model | Input | Output | Context | Features |
|---|
MiniMax-M2.5 | $0.14 | $0.75 | 256K | Long context + multimodal |
Moonshot Kimi
| Model | Input | Output | Context | Features |
|---|
Kimi-K2.5 | $0.15 | $2.00 | 128K | Long document processing, top Chinese |
Billing
| Category | Description | Cost |
|---|
| Input | Content you send to the model (prompt) | Base price |
| Output | Content the model generates | 3-5× input |
| Cache write | First-time prompt caching | 1.25× input |
| Cache read | Cache hit | 0.1× input |
- Prices may change with upstream providers; check the Model Marketplace for live rates
- Failed requests are not charged
Save Money
- Choose the right model — use cheaper models (DeepSeek-V3.2, GLM-5.1) for simple tasks
- Keep prompts concise — shorter input = fewer tokens = lower cost
- Control output length — set
max_tokens to limit output
- Leverage caching — fixed system prompts are cached automatically at 10% of input price
- Reduce context — don’t include unnecessary conversation history
Check Live Pricing
Log in to Anyone Dashboard → Model Marketplace to see real-time input/output pricing on each model card.
Usage Example
All models use the same OpenAI-compatible API — just change the model parameter:
from openai import OpenAI
client = OpenAI(
base_url="https://api.anyone.ai/v1",
api_key="your-anyone-token",
)
# GPT-5.4
response = client.chat.completions.create(
model="gpt-5.4",
messages=[{"role": "user", "content": "Hello!"}]
)
# Claude Opus 4.6
response = client.chat.completions.create(
model="claude-opus-4-6",
messages=[{"role": "user", "content": "Hello!"}]
)
# DeepSeek V3.2
response = client.chat.completions.create(
model="DeepSeek-V3.2",
messages=[{"role": "user", "content": "你好！"}]
)
