Unified model routing with OpenAI and Anthropic compatible endpoints
https://api.ai4u.nowv6.8.24Send your first request using the unified model alias opus-4.6
curl https://api.ai4u.now/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "opus-4.6",
"messages": [
{
"role": "user",
"content": "Hello, world!"
}
]
}'Simple model names that route to the best provider for your workload
| Model Alias | Description | Context | Avg / Median Latency |
|---|---|---|---|
TEXT opus-4.6 | Most capable reasoning model | 1M | 4.11s |
TEXT sonnet-4.6 | Latest Claude model | 200K | 5.77s |
TEXT haiku-4.5 | Fast, efficient responses | 200K | 2.90s |
TEXT gemini-3.1-pro | Most capable multimodal reasoning | 1M | 3.00s |
TEXT gemini-3-flash | Fast multimodal processing | 1M | 15.96s |
TEXT gpt-5.3-codex | Specialized for code generation and analysis | 400K | 1.58s |
EMBED text-embedding-005 | Versatile text embedding, 768 dimensions | -- | 0.88s |
EMBED gemini-embedding-001 | Multimodal embedding, 3072 dimensions | -- | 2.08s |
IMAGE imagen-4-ultra-001 | Ultra-high quality image generation | -- | -- |
IMAGE imagen-4-fast-001 | Fast image generation | -- | -- |
IMAGE gemini-3-pro-image-preview | AI-powered image generation (preview) | -- | -- |
VIDEO veo-3.1-generate-001 | Video generation, 5-30s duration, up to 4K resolution | -- | -- |
/v1/chat/completionsOpenAI-compatible chat completions endpoint
/v1/messagesAnthropic-compatible messages endpoint
/v1/embeddingsGenerate text embeddings for semantic search
/v1/images/generationsGenerate images from text prompts
/v1/videos/generationsGenerate videos from text prompts (async)
/v1/interactionsGemini multimodal interactions (text, image, video)
/v1/modelsList available models and aliases
from openai import OpenAI
client = OpenAI(
base_url="https://api.ai4u.now/v1",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="opus-4.5",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.ai4u.now/v1',
apiKey: process.env.AI4U_API_KEY,
});
const response = await client.chat.completions.create({
model: 'opus-4.5',
messages: [
{ role: 'user', content: 'Hello!' }
],
});
console.log(response.choices[0].message.content);