import OpenAI from 'openai';
// Drop-in replacement — just change the baseURL
const client = new OpenAI({
baseURL: 'https://api.assisters.dev/v1',
apiKey: process.env.ASSISTERS_API_KEY,
});
const response = await client.chat.completions.create({
model: 'assisters-chat-v1',
messages: [{ role: 'user', content: 'Hello!' }],
stream: true,
});
|Works seamlessly with your stack
From zero to production in under a minute.
Sign up free in 30 seconds. No credit card required.
Generate your key instantly from the developer dashboard.
Production-ready in under 60 seconds.
< 60s
Average time to first API response from signup
Four production-ready endpoints. One unified API. One API key.
Build conversational AI applications with streaming support. OpenAI-compatible API — migrate in minutes.
const stream = await client.chat.completions.create({
model: 'assisters-chat-v1',
messages: [{role: 'user', content: 'Hello'} ],
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}Generate dense vector representations for semantic search, RAG pipelines, and similarity matching at scale.
const result = await client.embeddings.create({
model: 'assisters-embed-v1',
input: 'The quick brown fox',
});
// 1024-dimensional vector
const vector = result.data[0].embedding;
console.log(vector.length); // 1024Detect harmful, unsafe, or policy-violating content with sub-100ms response times. Protect your users at scale.
const result = await client.moderations.create({
model: 'assisters-moderation-v1',
input: userMessage,
});
if (result.results[0].flagged) {
console.warn('Content flagged');
}Boost search relevance by re-scoring candidate documents with a cross-encoder. Dramatically improves RAG accuracy.
const ranked = await fetch(
'https://api.assisters.dev/v1/rerank',
{ method: 'POST',
body: JSON.stringify({
model: 'assisters-rerank-v1',
query: 'AI inference API',
documents: docs,
},
}
);One API, every runtime. Migrate from OpenAI in under 2 minutes.
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.assisters.dev/v1',
apiKey: process.env.ASSISTERS_API_KEY,
});
const chat = await client.chat.completions.create({
model: 'assisters-chat-v1',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(chat.choices[0].message.content);from openai import OpenAI
client = OpenAI(
base_url='https://api.assisters.dev/v1',
api_key=os.environ['ASSISTERS_API_KEY'],
)
response = client.chat.completions.create(
model='assisters-chat-v1',
messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.choices[0].message.content)curl https://api.assisters.dev/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $ASSISTERS_API_KEY" \
-d '{
"model": "assisters-chat-v1",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'package main
import (
"context"
openai "github.com/sashabaranov/go-openai"
)
cfg := openai.DefaultConfig(apiKey)
cfg.BaseURL = "https://api.assisters.dev/v1"
client := openai.NewClientWithConfig(cfg)
resp, _ := client.CreateChatCompletion(
context.Background(),
openai.ChatCompletionRequest{
Model: "assisters-chat-v1",
},
)State-of-the-art open-source models for every use case.
Start free, pay as you grow. No hidden fees, no surprises.
$0/mo
Perfect for prototyping
$29/mo
For production apps
Custom
For teams at scale
| Feature | Free | Developer | Enterprise |
|---|---|---|---|
| Free tokens/month | 100K | 5M | Unlimited |
| Rate limit (RPM) | 10 | 100 | Custom |
| Chat completions | |||
| Embeddings | |||
| Moderation | |||
| Reranking | |||
| Usage dashboard | — | ||
| Email support | — | ||
| SLA guarantee | — | — | |
| Dedicated support | — | — |
100% transparent. No surprise bills. View full pricing →
Assisters API is a drop-in replacement for OpenAI that uses the same SDK and API format. The key differences are proprietary models optimized for specific tasks, usage-based pricing that's up to 70% cheaper, and guaranteed 99.9% uptime SLA. Migration takes minutes—just change your base URL to https://api.assisters.dev/v1 and swap your API key.
Assisters-embed-v1 is specifically optimized for multilingual retrieval with 100+ language support and 1024-dimensional vectors. Unlike English-first models, it maintains semantic accuracy across language pairs, making it ideal for global RAG systems. Combined with assisters-rerank-v1, you get a complete multilingual search pipeline at a fraction of competitor costs.
Yes. Assisters API is enterprise-ready with 99.9% uptime SLA backed by service agreements, <100ms P95 latency for inference endpoints, and SOC 2 Type II compliance. Dedicated support is available for paid plans. Companies process millions of tokens daily through our infrastructure without issues.
Assisters uses transparent per-token pricing with no hidden fees. You pay for exactly what you use: input tokens (prompts) and output tokens (completions) are priced separately. Free tier includes 100K tokens/month. Subscription plans include token allowances plus volume discounts. Wallet credits never expire, letting you prepay for predictable budgeting.
Get your API key in 30 seconds. Build your first integration in under a minute. Scale to millions of requests without changing a line of code.