Base URL: https://api.boundlessapi.com/v1
Auth: Bearer API key from Dashboard
Example model: claude-sonnet-4-6
OpenAI SDK: change base_url (and API key). $5 on signup · no card required to start.
Get your first API call working in under 5 minutes. Use an exact live model ID below — wrong names (e.g. Claude Sonnet 4.6 with spaces) will fail.
Model IDs — use exact strings
⚠ Most common error
Requests fail with No available channel for model … when the model field does not match a live backend ID exactly.
- Wrong:
Claude Opus 4.8,gemini-2.5-pro,deepseek-v4-flash(not live yet) - Right:
claude-opus-4-8,claude-sonnet-4-6,gpt-5.5 - Also supported:
gpt-5.6-luna,gpt-5.6-sol,gpt-5.6-terra
Thirteen models are live today. The rest of our 49-model catalog is marked Coming soon on the Models page. Fetch live IDs anytime with GET /v1/models or from Dashboard → Models.
1. Create an Account
- Go to https://boundlessapi.com
- Click Start free — sign up with email, Google, or GitHub
- We add $5.00 to your account balance — no credit card required
2. Create an API Key
- Open Dashboard → API Keys
- Click Create Key
- Name it (e.g.,
dev-local) - Copy the key now
3. Try the Playground
The fastest way to confirm everything works — no terminal or SDK required.
- Sign in to the Dashboard
- Open Playground in the sidebar
- Pick a model from the dropdown (e.g.,
claude-sonnet-4-6) - Type a message and send — you should get a reply within seconds
When you are ready to integrate into your own app or script, continue to Step 4.
4. Make Your First Request
To call the API from your terminal or code:
Base URL: https://api.boundlessapi.com/v1
cURL
curl https://api.boundlessapi.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "claude-sonnet-4-6",
"messages": [{"role": "user", "content": "Hello!"}]
}'
Python (OpenAI SDK)
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.boundlessapi.com/v1",
)
response = client.chat.completions.create(
model="claude-sonnet-4-6",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
TypeScript (OpenAI SDK)
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.BOUNDLESS_API_KEY,
baseURL: "https://api.boundlessapi.com/v1",
});
const response = await client.chat.completions.create({
model: "claude-sonnet-4-6",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);
5. Check Usage
Dashboard → Activity shows each request: model, tokens, cost, latency.
6. Next Steps
| Topic | Doc |
|---|---|
| API keys & security | Authentication |
| All endpoints | API Reference |
| Model list | Models |
| Rate limits | Rate Limits |
| Billing | How Billing Works |
| Migrate from OpenRouter | Migrating from OpenRouter |
| Prompt caching | Prompt Caching |
Troubleshooting
| Problem | Fix |
|---|---|
401 invalid_api_key |
Check key, ensure Bearer prefix |
402 insufficient_quota |
Add credits in Billing |
429 rate_limit_exceeded |
Slow down; see Rate Limits |
model_not_found / no available channel |
Use a live model ID from the sidebar — copy-paste, no spaces. See Model IDs. |
Full list: Error Codes
Support
- FAQ
- Discord #support
- support@boundlessapi.com