Per-key metering
Scoped and quoted in writing- OpenAI-compatible endpoint
- Usage metered per API key
- Prepaid or invoiced
- Team keys, rate limits, usage reports
Qwen, DeepSeek and GLM behind a single OpenAI-compatible endpoint. Use the model ID in the model field of any request to https://api.aaronalphax.com/v1.
Platform pages are in English. الصفحة الرئيسية بالعربية ←
| Model ID | Provider | Modality | Context | Price / 1M |
|---|---|---|---|---|
| qwen-maxFlagship Qwen tier for complex, multi-step tasks. | Alibaba · Qwen | Text | 32K | On request |
| qwen-plusBalanced performance, speed and cost; long context. | Alibaba · Qwen | Text | 1M | On request |
| qwen-flashFast, cost-efficient Qwen tier. | Alibaba · Qwen | Text | 1M | On request |
| qwen-turboLegacy fast tier, kept for existing integrations. | Alibaba · Qwen | Text | On request | On request |
| deepseek-v4-proDeepSeek's top tier for reasoning and coding. | DeepSeek | Text · Reasoning | 1M | On request |
| deepseek-flashHigh-throughput DeepSeek tier at low cost. | DeepSeek | Text · Reasoning · Vision | 1M | On request |
| deepseek-v3Earlier general model; alias for existing integrations. | DeepSeek | Text | On request | On request |
| deepseek-r1Earlier reasoning model; alias for existing integrations. | DeepSeek | Text · Reasoning | On request | On request |
| glm-5.3Zhipu's latest bilingual model for agents and coding. | Zhipu · GLM | Text · Agents | 1M | On request |
| glm-5Bilingual model for enterprise assistants. | Zhipu · GLM | Text · Agents | 198K | On request |
| glm-4Earlier GLM generation for existing integrations. | Zhipu · GLM | Text | On request | On request |
| text-embedding-v4Text embeddings for search and RAG via /v1/embeddings. | Alibaba · Qwen | Embeddings | On request | On request |
| Model ID | Provider | Modality | Context | Capabilities | Price / 1M (in / out) | Status |
|---|
No models match those filters.
Context windows are the upstream maximums published by Alibaba Cloud Model Studio and DeepSeek as of November 2026; limits on your key are set in your contract. "On request" means we confirm the figure for your deployment. Legacy models remain available for existing integrations. Pricing is quoted per workload in USD within 1 business day — model availability and pricing are confirmed per contract; price sorting activates per model once list prices are published. Model names are trademarks of their respective owners.
Usage is metered per API key, prepaid or invoiced, on one consolidated monthly statement. Pricing is quoted per workload in USD within 1 business day.
Only the model value changes. Your messages, tools and streaming code stay identical.
curl https://api.aaronalphax.com/v1/chat/completions \
-H "Authorization: Bearer $AAX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen-plus",
"messages": [
{"role": "system", "content": "Be concise."},
{"role": "user", "content": "Summarise Q3 in Arabic."}
]
}'# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.aaronalphax.com/v1",
api_key="YOUR_AAX_API_KEY",
)
resp = client.chat.completions.create(
model="qwen-plus", # switch models by changing one parameter
messages=[{"role": "user", "content": "Hello from Dubai"}],
)
print(resp.choices[0].message.content)// npm install openai
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.aaronalphax.com/v1",
apiKey: process.env.AAX_API_KEY,
});
const resp = await client.chat.completions.create({
model: "qwen-plus",
messages: [{ role: "user", content: "Hello from Singapore" }],
});
console.log(resp.choices[0].message.content);