AetherComputee API Documentation
Complete public reference guide for integrating OpenAI and Anthropic SDKs, Cursor IDE, 9Router, and custom agents to AetherComputee serverless AI gateway.
1. Overview & Base URL
AetherComputee provides zero-latency serverless access to 40 commercial and open-weights flagship AI models (including Claude Opus 4.8, GPT-5.6 Sol, Gemini 3.6 Flash, and DeepSeek V4). All API endpoints follow standard OpenAI REST and SSE formats.
API Base URL:
https://api.aethercomputee.com/v1
Note: Always use
https://api.aethercomputee.com/v1
Note: Always use
https://api.aethercomputee.com/v1 as the Base URL for your API requests.
2. Authentication
Authenticate your HTTP requests by passing your API key in the request headers using standard Bearer authorization:
Authorization: Bearer ae_live_YOUR_API_KEY
Generate secure API keys instantly inside your AetherComputee Console under the API Keys tab.
3. Quickstart Code Snippets
Python (Official OpenAI Library)
import openai
client = openai.OpenAI(
base_url="https://api.aethercomputee.com/v1",
api_key="ae_live_YOUR_API_KEY"
)
response = client.chat.completions.create(
model="claude-opus-4.8",
messages=[{"role": "user", "content": "Hello AetherComputee!"}]
)
print(response.choices[0].message.content)
Node.js / TypeScript
import OpenAI from "openai";
const openai = new OpenAI({
baseURL: "https://api.aethercomputee.com/v1",
apiKey: "ae_live_YOUR_API_KEY"
});
async function main() {
const completion = await openai.chat.completions.create({
messages: [{ role: "user", content: "Hello from Node!" }],
model: "claude-3.5-sonnet",
});
console.log(completion.choices[0].message.content);
}
main();
4. Image Generation (Flux.1 & DALL-E)
Generate high-quality images using models like flux.
Python Example
import openai
client = openai.OpenAI(
base_url="https://api.aethercomputee.com/v1",
api_key="ae_live_YOUR_API_KEY"
)
response = client.images.generate(
model="flux",
prompt="A futuristic cyberpunk city with neon lights and flying cars, digital art",
n=1,
size="1024x1024"
)
print(response.data[0].url)
5. Video Generation (CogVideoX & AnimateDiff)
Generate high-quality AI videos from text prompts using models like cogvideox.
Endpoint:
Rate:
POST https://api.aethercomputee.com/v1/video/generationsRate:
$0.15 / Video (7 Videos / $1)
cURL Terminal Command
curl -X POST https://api.aethercomputee.com/v1/video/generations \
-H "Authorization: Bearer ae_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "cogvideox",
"prompt": "A cinematic drone shot of a misty mountain range at sunset"
}'
6. Text-to-Speech Generation
Generate human-like speech from text using models like tts-1.
Python Example
import openai
import os
client = openai.OpenAI(
base_url="https://api.aethercomputee.com/v1",
api_key="ae_live_YOUR_API_KEY"
)
response = client.audio.speech.create(
model="tts-1",
voice="alloy",
input="Welcome to AetherComputee, the world's fastest API gateway."
)
response.stream_to_file("output.mp3")
cURL Terminal Command
curl -X POST https://api.aethercomputee.com/v1/chat/completions \
-H "Authorization: Bearer ae_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-4.8",
"messages": [{"role": "user", "content": "Hello AetherComputee!"}]
}'
4. POST /v1/chat/completions
Generates model completion text for a structured list of conversation messages.
Endpoint:
Headers:
POST https://api.aethercomputee.com/v1/chat/completionsHeaders:
Authorization: Bearer ae_live_... | Content-Type: application/json
5. GET /v1/models
Returns the complete list of 40 available models in OpenAI JSON catalog format for auto-import in tools like 9Router, LiteLLM, and Cursor IDE.
curl -X GET https://api.aethercomputee.com/v1/models
6. SSE Real-Time Streaming
Pass "stream": true in your POST request body to receive real-time streaming tokens using Server-Sent Events (SSE `data: {...}\n\n` format).
7. 9Router Proxy Setup
- Open 9Router Proxy Dashboard.
- Add Custom OpenAI-Compatible Provider.
- Set Base URL to:
https://api.aethercomputee.com/v1 - Set API Key to your active key:
ae_live_... - Click Import from /models — all 40 models will auto-import cleanly!
VS Code / Cursor chatLanguageModels.json Setup
To configure AetherComputee models in VS Code / Cursor custom language models configuration (chatLanguageModels.json):
[
{
"name": "aether",
"vendor": "customendpoint",
"apiKey": "ae_live_YOUR_API_KEY",
"apiType": "chat-completions",
"models": [
{
"id": "claude-opus-4.8",
"name": "Claude Opus 4.8 (AetherComputee)",
"url": "https://api.aethercomputee.com/v1/chat/completions",
"toolCalling": true,
"vision": true,
"maxInputTokens": 128000,
"maxOutputTokens": 16000
}
]
}
]
8. Full 40 Models Catalog & Identifiers
All model IDs below are 100% active and supported on the gateway:
| Model ID | Category / Tier | Description | Official API Rate (Input / Output 1M) |
|---|---|---|---|
| Claude 3.5 Sonnet (Most Used Text) | claude-3.5-sonnet | Text Flagship | $1.50 / $4.50 1M |
| Flux.1 Dev (Most Used Image) | flux | Image Generator | $0.067 / Image (15 imgs / $1) |
| TTS-1 (Most Used Audio) | tts-1 | Text-to-Speech | $0.80 / Sec |
| DALL-E 3 (OpenAI) | dall-e-3 | Image Generator | $0.125 / Image (8 imgs / $1) |
| TTS-1 HD (OpenAI High-Def Voice) | tts-1-hd | Text-to-Speech | $0.05 / Sec |
| Claude Fable 5 (Anthropic) | claude-fable-5 | Top Coding Flagship (SWE-bench 95%) | $3.00 / $15.00 1M |
| GPT-5.6 Sol (max) (OpenAI) | gpt-5.6-sol | Top Science & Logic Model | $2.50 / $10.00 1M |
| GPT-5.5 Pro (OpenAI) | gpt-5.5-pro | Enterprise Frontier Standard | $2.00 / $8.00 1M |
| Claude Sonnet 5 (Anthropic) | claude-sonnet-5 | Balanced High-Performance | $1.50 / $7.50 1M |
| Gemini 3.6 Flash (Google) | gemini-3.6-flash | Fastest 1M Context Workhorse | $0.10 / $0.40 1M |
| Grok 4.5 (xAI) | grok-4.5 | Coding & Reasoning Frontier | $2.00 / $10.00 1M |
| Gemini 3.1 Pro (Google) | gemini-3.1-pro | Deep Multimodal Reasoning | $1.25 / $5.00 1M |
| GPT-4o (OpenAI) | gpt-4o | Multimodal Flagship Standard | $2.50 / $10.00 1M |
| Claude 3.5 Sonnet (Anthropic) | claude-3.5-sonnet | Global Developer Standard | $3.00 / $15.00 1M |
| GPT-4o-mini (OpenAI) | gpt-4o-mini | Fast & Cheap API Model | $0.15 / $0.60 1M |
| o1 (OpenAI) | o1 | Deep Reasoning Specialist | $15.00 / $60.00 1M |
| o3-mini (OpenAI) | o3-mini | Compact STEM Reasoning | $1.10 / $4.40 1M |
| Claude 3.5 Haiku (Anthropic) | claude-3.5-haiku | Lightning Fast API Model | $0.80 / $4.00 1M |
| Gemini 1.5 Pro (Google) | gemini-1.5-pro | Long-Context Enterprise | $1.25 / $5.00 1M |
| Gemini 3.5 Flash-Lite (Google) | gemini-3.5-flash-lite | Ultra-Sasta $0.075/1M Model | $0.075 / $0.30 1M |
| Gemini 1.5 Flash (Google) | gemini-1.5-flash | High-Volume Fast Model | $0.075 / $0.30 1M |
| Claude 3 Opus (Anthropic) | claude-3-opus | Original Heavy Model | $15.00 / $75.00 1M |
| Grok 2 (xAI) | grok-2 | Real-Time Data Model | $2.00 / $10.00 1M |
| GLM-5.2 (753B) (Zhipu AI) | glm-5.2 | #1 Open Coding Model (Claude Level) | $5.50 / $22.00 1M |
| Kimi K3 (2.8T MoE) (Moonshot AI) | kimi-k3 | #1 1M Context Frontier Engine | $5.50 / $22.00 1M |
| DeepSeek V4 Pro (DeepSeek) | deepseek-v4-pro | 1.6T MoE Flagship | $0.27 / $1.10 1M |
| Qwen 3.6 (35B) (Alibaba) | qwen-3.6-35b | Top Multi-lingual Open Engine | $0.20 / $0.60 1M |
| Llama 4 Scout (Meta) | llama-4-scout | 10M Context Window RAG King | $0.30 / $0.90 1M |
| MiniMax M3 | minimax-m3 | BenchLM Coding Leader | $0.25 / $0.85 1M |
| Gemma 4 12B (Google) | gemma-4-12b | Top Single-GPU Model | $0.10 / $0.30 1M |
| MiMo-V2.5-Pro (Xiaomi) | mimo-v2.5-pro | Multimodal Audio/Video Model | $0.20 / $0.60 1M |
| Inkling (975B) (Thinking Machines) | inkling-975b | Apache 2.0 Open Base | $0.30 / $0.90 1M |
| Muse Spark 1.1 (Meta Ecosystem) | muse-spark-1.1 | Commercial Open Model | $0.20 / $0.60 1M |
| DeepSeek-V3 | deepseek-v3 | Global Standard Open Model | $0.14 / $0.28 1M |
| DeepSeek-R1 | deepseek-r1 | Open Reasoning Engine | $0.55 / $2.19 1M |
| Qwen-2.5-72B-Instruct | qwen-2.5-72b | Reliable Open Workhorse | $0.35 / $0.40 1M |
| Llama-3.3-70B-Instruct | llama-3.3-70b | Meta Open Standard | $0.23 / $0.40 1M |
| DeepSeek-R1-Distill-70B | deepseek-r1-distill-70b | Math & Logic Specialist | $0.23 / $0.40 1M |
| Mixtral-8x22B | mixtral-8x22b | High-Concurrency MoE Engine | $0.60 / $0.60 1M |
| Yi-Lightning (01.AI) | yi-lightning | Fast Inference Model | $0.20 / $0.20 1M |
| DeepSeek-Coder-V2 | deepseek-coder-v2 | 236B Coding Specialist | $0.14 / $0.28 1M |
| Sarvam-2B (Sarvam AI) | sarvam-2b | Indian Language Specialist | $0.10 / $0.10 1M |
| SmolLM2-1.7B | smollm2-1.7b | Micro Edge Device Engine | $0.04 / $0.04 1M |
9. Plans & Rate Limits (RPM / Allowance)
| Model ID | Category / Tier | Description | Official API Rate (Input / Output 1M) |
|---|---|---|---|
| Claude 3.5 Sonnet (Most Used Text) | claude-3.5-sonnet | Text Flagship | $1.50 / $4.50 1M |
| Flux.1 Dev (Most Used Image) | flux | Image Generator | $0.067 / Image (15 imgs / $1) |
| TTS-1 (Most Used Audio) | tts-1 | Text-to-Speech | $0.80 / Sec |
| DALL-E 3 (OpenAI) | dall-e-3 | Image Generator | $0.125 / Image (8 imgs / $1) |
| TTS-1 HD (OpenAI High-Def Voice) | tts-1-hd | Text-to-Speech | $0.05 / Sec |
| Claude Fable 5 (Anthropic) | claude-fable-5 | Top Coding Flagship (SWE-bench 95%) | $3.00 / $15.00 1M |
| GPT-5.6 Sol (max) (OpenAI) | gpt-5.6-sol | Top Science & Logic Model | $2.50 / $10.00 1M |
| GPT-5.5 Pro (OpenAI) | gpt-5.5-pro | Enterprise Frontier Standard | $2.00 / $8.00 1M |
| Claude Sonnet 5 (Anthropic) | claude-sonnet-5 | Balanced High-Performance | $1.50 / $7.50 1M |
| Gemini 3.6 Flash (Google) | gemini-3.6-flash | Fastest 1M Context Workhorse | $0.10 / $0.40 1M |
| Grok 4.5 (xAI) | grok-4.5 | Coding & Reasoning Frontier | $2.00 / $10.00 1M |
| Gemini 3.1 Pro (Google) | gemini-3.1-pro | Deep Multimodal Reasoning | $1.25 / $5.00 1M |
| GPT-4o (OpenAI) | gpt-4o | Multimodal Flagship Standard | $2.50 / $10.00 1M |
| Claude 3.5 Sonnet (Anthropic) | claude-3.5-sonnet | Global Developer Standard | $3.00 / $15.00 1M |
| GPT-4o-mini (OpenAI) | gpt-4o-mini | Fast & Cheap API Model | $0.15 / $0.60 1M |
| o1 (OpenAI) | o1 | Deep Reasoning Specialist | $15.00 / $60.00 1M |
| o3-mini (OpenAI) | o3-mini | Compact STEM Reasoning | $1.10 / $4.40 1M |
| Claude 3.5 Haiku (Anthropic) | claude-3.5-haiku | Lightning Fast API Model | $0.80 / $4.00 1M |
| Gemini 1.5 Pro (Google) | gemini-1.5-pro | Long-Context Enterprise | $1.25 / $5.00 1M |
| Gemini 3.5 Flash-Lite (Google) | gemini-3.5-flash-lite | Ultra-Sasta $0.075/1M Model | $0.075 / $0.30 1M |
| Gemini 1.5 Flash (Google) | gemini-1.5-flash | High-Volume Fast Model | $0.075 / $0.30 1M |
| Claude 3 Opus (Anthropic) | claude-3-opus | Original Heavy Model | $15.00 / $75.00 1M |
| Grok 2 (xAI) | grok-2 | Real-Time Data Model | $2.00 / $10.00 1M |
| GLM-5.2 (753B) (Zhipu AI) | glm-5.2 | #1 Open Coding Model | $0.40 / $1.20 1M |
| Kimi K3 (2.8T MoE) (Moonshot AI) | kimi-k3 | #1 1M Context Open Model | $0.50 / $1.50 1M |
| DeepSeek V4 Pro (DeepSeek) | deepseek-v4-pro | 1.6T MoE Flagship | $0.27 / $1.10 1M |
| Qwen 3.6 (35B) (Alibaba) | qwen-3.6-35b | Top Multi-lingual Open Engine | $0.20 / $0.60 1M |
| Llama 4 Scout (Meta) | llama-4-scout | 10M Context Window RAG King | $0.30 / $0.90 1M |
| MiniMax M3 | minimax-m3 | BenchLM Coding Leader | $0.25 / $0.85 1M |
| Gemma 4 12B (Google) | gemma-4-12b | Top Single-GPU Model | $0.10 / $0.30 1M |
| MiMo-V2.5-Pro (Xiaomi) | mimo-v2.5-pro | Multimodal Audio/Video Model | $0.20 / $0.60 1M |
| Inkling (975B) (Thinking Machines) | inkling-975b | Apache 2.0 Open Base | $0.30 / $0.90 1M |
| Muse Spark 1.1 (Meta Ecosystem) | muse-spark-1.1 | Commercial Open Model | $0.20 / $0.60 1M |
| DeepSeek-V3 | deepseek-v3 | Global Standard Open Model | $0.14 / $0.28 1M |
| DeepSeek-R1 | deepseek-r1 | Open Reasoning Engine | $0.55 / $2.19 1M |
| Qwen-2.5-72B-Instruct | qwen-2.5-72b | Reliable Open Workhorse | $0.35 / $0.40 1M |
| Llama-3.3-70B-Instruct | llama-3.3-70b | Meta Open Standard | $0.23 / $0.40 1M |
| DeepSeek-R1-Distill-70B | deepseek-r1-distill-70b | Math & Logic Specialist | $0.23 / $0.40 1M |
| Mixtral-8x22B | mixtral-8x22b | High-Concurrency MoE Engine | $0.60 / $0.60 1M |
| Yi-Lightning (01.AI) | yi-lightning | Fast Inference Model | $0.20 / $0.20 1M |
| DeepSeek-Coder-V2 | deepseek-coder-v2 | 236B Coding Specialist | $0.14 / $0.28 1M |
| Sarvam-2B (Sarvam AI) | sarvam-2b | Indian Language Specialist | $0.10 / $0.10 1M |
| SmolLM2-1.7B | smollm2-1.7b | Micro Edge Device Engine | $0.04 / $0.04 1M |