LLM API — Access 94+ AI Models from $5/mo

Supported Models

Access the world's leading open-source and frontier models through a single OpenAI-compatible API. All models available from the $5/mo Hobbyist plan.

Showing 8 of 94+ available models. Browse all models →

Hobbyist Plan Limits

The $5/mo Hobbyist plan is designed to cover prototyping, personal projects, and small-scale applications. 3-day trial, then $5/mo — your allocation renews every month.

Code Examples

The AINative API is fully OpenAI-compatible. If you already use the OpenAI SDK, just change the base URL and model name. For direct HTTP calls, authenticate with theX-API-Keyheader. Both /v1and /api/v1prefixes work and serve the same model catalog.

from openai import OpenAI

client = OpenAI(
    api_key="ain_...",  # Your AINative API key
    base_url="https://api.ainative.studio/v1",
)

response = client.chat.completions.create(
    model="meta/llama-3.3-70b-instruct",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum entanglement simply."},
    ],
    max_tokens=512,
)

print(response.choices[0].message.content)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'ain_...',
  baseURL: 'https://api.ainative.studio/v1',
});

const response = await client.chat.completions.create({
  model: 'mistralai/mistral-7b-instruct',
  messages: [
    { role: 'user', content: 'What are the best practices for API design?' },
  ],
  stream: true,
});

for await (const chunk of response) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}

# Direct API calls authenticate with the X-API-Key header.
# Both /v1 and /api/v1 prefixes work (same catalog).
curl https://api.ainative.studio/api/v1/chat/completions \
  -H "X-API-Key: ain_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2",
    "messages": [
      {"role": "user", "content": "Write a Python function to reverse a string."}
    ],
    "max_tokens": 256
  }'

Pricing Tiers

Start with a 3-day trial, then $5/mo, then pay as you grow from $5/mo. All plans include the full model catalog. Token usage is billed at per-model rates shown in the model table above.

AINative vs OpenAI vs Anthropic Pricing

Open-source models on AINative are 10–25x cheaper than comparable closed-source alternatives. For many workloads, Llama 3.3 70B matches or exceeds GPT-4o quality at a fraction of the cost.

Prices shown are per 1M input tokens. Output tokens are billed separately. OpenAI and Anthropic prices as of 2026-06.

Integrate programmatically

AINative is agent-native. Every surface below is machine-readable so an autonomous agent can discover, authenticate, and start building with zero human handoff. Authenticate with the X-API-Key header. Both the /v1 and /api/v1 prefixes serve the same catalog.

Machine-readable surfaces

Zero-auth on-ramp

Provision a working database with a single unauthenticated request — no signup, no key. Perfect for an agent that needs storage in the first second.

curl -X POST https://api.ainative.studio/api/v1/public/instant-db \
  -H "Content-Type: application/json" \
  -d '{}'

SDKs and CLI

Skip hand-rolling HTTP calls — install a typed client for your stack.

npm install @ainative/sdk

npm install @ainative/react-sdk

npm install @ainative/next-sdk

npm install @ainative/ai-sdk-provider

npm install -g zerodb-cli

MCP servers

Wire AINative into any MCP-capable agent (Claude Code, Cursor, and more) with one command.

npx ainative-memory-mcp

npx ainative-prd-mcp

npx ainative-zerodb-memory-mcp

npx ainative-zerodb-mcp-server

Frequently Asked Questions