16 AI Models · 4 Providers · One Endpoint

One API.
16 Models.
Zero Lock-in.

Drop in OriginalPoint as your AI gateway. Get instant access to GPT-5, Claude Opus 4.5, Gemini 3 Pro, and 13 more — with smart routing that auto-selects the best model for each request.

No credit card required · OpenAI-compatible · Sub-50ms routing

from openai import OpenAI

# Drop-in replacement — no code changes needed
client = OpenAI(
  api_key="op_your_key_here",
  base_url="https://api.originalpoint.ai/v1"
)

response = client.chat.completions.create(
  model="auto",  # Smart routing picks best model
  messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)
import OpenAI from 'openai';

// Same SDK, new base URL — that's it
const client = new OpenAI({
  apiKey: 'op_your_key_here',
  baseURL: 'https://api.originalpoint.ai/v1'
});

const response = await client.chat.completions.create({
  model: 'claude-opus-4.5',
  messages: [{role: 'user', content: 'Hello!'}]
});

console.log(response.choices[0].message.content);
curl https://api.originalpoint.ai/v1/chat/completions \
  -H "Authorization: Bearer op_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "stream": true
  }'

# ← Works with any OpenAI-compatible client
# Use "auto" to let smart routing decide
Connected to api.originalpoint.ai ↗ 38ms latency
0
Models Available
0
Top Providers
99.9%
Uptime SLA
$0
Setup Cost
Smart Routing

The right model for every request, automatically.

OriginalPoint's routing engine analyzes your request in real-time and selects the optimal model based on cost, latency, and capability — no manual model selection needed.

  • Cost routing: always uses cheapest model that meets quality bar
  • Latency routing: selects lowest-latency provider for time-sensitive tasks
  • Reliability routing: auto-failover if a provider is degraded
  • Override anytime: pin to a specific model per-request
Read routing docs →
routing-demo.py
# Use "auto" — we handle the rest
response = client.chat.completions.create(
  model="auto",
  messages=[...],
  extra_body={
    "routing": "cost"  # or "latency" | "reliability"
  }
)

# Response includes routing metadata
print(response.model)  # → "gpt-5-mini"
print(response.usage.cost_usd)  # → 0.000023
Routed to: gpt-5-mini
Latency: 34ms
Cost saved: 76%
Bring Your Own Keys

Use your own provider keys. Pay provider rates.

BYOK lets you connect your existing OpenAI, Anthropic, or Google API keys. OriginalPoint routes through your credentials — you pay provider rates directly, we charge only a small routing fee.

  • Connect keys from OpenAI, Anthropic, Google, xAI
  • Your credentials never leave your account in plain text
  • Routing fee: $0.50/1M tokens regardless of model
  • Spend analysis: see costs broken down by provider
Learn about BYOK →
Connected Keys
OpenAI sk-••••••••••9F3a
Active
Anthropic sk-••••••••••7Kp1
Active
Google
+ Connect
This month's routing fee
$1.24
vs. $47.80 on hosted plans
Usage Analytics

Full visibility into every token and dollar.

Real-time dashboards show you exactly what you're spending, on which models, for which use cases. Set budgets, alerts, and per-project cost caps.

  • Per-model breakdown: tokens, requests, cost
  • Time-series charts: hourly, daily, monthly views
  • Budget alerts: email/webhook when threshold hit
  • Export to CSV, connect to your data warehouse
View dashboard demo →
Monthly Usage — April 2026
4.2M
Total tokens
$12.40
Total cost
8,341
Requests
Cost by model
GPT-5
$8.06
Claude Sonnet 4
$3.47
GPT-5 mini
$0.87
Enterprise Security

Built for teams with strict compliance requirements.

SOC 2 Type II compliant. Your prompts and responses are never stored or used for training. Enterprise plans include SSO, audit logs, and dedicated infrastructure.

  • SOC 2 Type II certified (report available on request)
  • Zero data retention — no prompt logging by default
  • SSO via SAML 2.0, OIDC (Okta, Azure AD, Google)
  • Audit log: every API call, user, and model selection
  • VPC deployment available for Enterprise plans
Enterprise plans →
🔒
SOC 2 Type II
Certified · Last audit: Jan 2026
✓ Compliant
🛡️
Zero Data Retention
Prompts & responses never stored
✓ Active
📋
Audit Logging
Complete call history with user attribution
✓ Enabled
🔑
SSO / SAML 2.0
Okta · Azure AD · Google Workspace
Enterprise

Every model. One endpoint.

Switch between models with a single parameter change. No new SDKs, no new auth flows.

Model Context Input / 1M Output / 1M Tier
GPT-5 mini
OpenAI
128K
$0.15
$0.60
Fast
Grok Code Fast 1
xAI
131K
$0.08
$0.30
Fast
Gemini 3 Flash
Google
1M
$0.075
$0.30
Fast
GPT-5
OpenAI
128K
$2.50
$10.00
Versatile
GPT-5.1
OpenAI
128K
$3.00
$12.00
Versatile
Claude Sonnet 4
Anthropic
200K
$3.00
$15.00
Versatile
Claude Sonnet 4.5
Anthropic
200K
$3.00
$15.00
Versatile
Claude Haiku 4.5
Anthropic
200K
$0.80
$4.00
Versatile
GPT-5.2
OpenAI
128K
$3.50
$14.00
Versatile
GPT-4.1
OpenAI
128K
$2.00
$8.00
Versatile
GPT-4o
OpenAI
128K
$2.50
$10.00
Versatile
GPT-5.1-Codex-Max
OpenAI
256K
$15.00
$60.00
Powerful
Claude Opus 4.5
Anthropic
200K
$15.00
$75.00
Powerful
Claude Opus 4.1
Anthropic
200K
$12.00
$60.00
Powerful
Gemini 3 Pro
Google
2M
$3.50
$10.50
Powerful
Gemini 2.5 Pro
Google
1M
$1.25
$5.00
Powerful

From indie hackers to enterprise teams.

ACME AI
NovaTech
Synthex
Luminex
CoreAI
Stackline
"We cut our AI costs by 60% in the first week. Smart routing automatically switched us to cheaper models for simple tasks while keeping the heavy hitters for complex ones. It just works."
JK
James Kowalski
CTO, NovaTech AI · Building AI-native products
"The BYOK feature is a game changer. We bring our existing Anthropic and OpenAI credits, OriginalPoint just handles the routing layer. One API key, one SDK, access to everything."
SR
Sofia Rodriguez
Head of Platform, Synthex · 2M+ API requests/month

How much will it cost?

Drag the slider to estimate your monthly costs across tiers.

Monthly token volume 10M tokens
025M50M75M100M
⚡ Fast Tier
$0.75
GPT-5 mini / Gemini Flash
🔮 Versatile Tier
$25.00
GPT-5 / Claude Sonnet 4
💎 Powerful Tier
$150.00
Claude Opus / GPT-5.1-Codex-Max

Estimates based on average input/output ratio. See full pricing →

Start building in under 5 minutes.

Free tier includes 1M tokens/month. No credit card required.
OpenAI-compatible — your existing code works unchanged.