Quickstart
Authenticate, send a chat completion, and read the response using cURL or the OpenAI SDK.
- Base URL
https://jarbird.com/api/v1- Chat completions
POST /chat/completions
Get an API key
Jarbird is in invite-only beta. If you already have access, sign in and create a key in the dashboard. Set it in your server environment before running these examples.
export JARBIRD_API_KEY="your-jarbird-key"Send a request
Use an exact model ID from the catalogue. The examples send a single user message and read the assistant’s reply.
curl https://jarbird.com/api/v1/chat/completions \
-H "Authorization: Bearer $JARBIRD_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-sonnet-5.5",
"messages": [{"role": "user", "content": "Say hello."}]
}'python -m pip install openaiimport os
from openai import OpenAI
client = OpenAI(
base_url="https://jarbird.com/api/v1",
api_key=os.environ["JARBIRD_API_KEY"],
)
response = client.chat.completions.create(
model="anthropic/claude-sonnet-5.5",
messages=[{"role": "user", "content": "Say hello."}],
)
print(response.choices[0].message.content)npm install openaiimport OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://jarbird.com/api/v1",
apiKey: process.env.JARBIRD_API_KEY,
});
const response = await client.chat.completions.create({
model: "anthropic/claude-sonnet-5.5",
messages: [{ role: "user", content: "Say hello." }],
});
console.log(response.choices[0].message.content);See the GLM-5.3 Flash Abliterated reference for EU hosting details and pricing.
Read the response
For a non-streaming chat completion, read the reply at choices[0].message.content.
{
"model": "anthropic/claude-sonnet-5.5",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello!"
},
"finish_reason": "stop"
}
]
}Switch from OpenRouter
Set your client’s base URL to https://jarbird.com/api/v1 and replace its API key with a Jarbird key. Keep the same model ID if it’s supported. Test streaming, tools, and any provider preferences your app uses before moving production traffic.
Troubleshooting
| HTTP status | What to check |
|---|---|
| 400 | Check the JSON body, model ID, and request parameters. |
| 401 | Check that the Jarbird key is active and sent as a bearer token. |
| 402 | Check your prepaid balance and any applicable spend limits. |
| 429 | Reduce request frequency or concurrency and retry with backoff. |
Frequently asked questions
Do I need a different SDK?
You can use the OpenAI SDK for chat completions. Set the base URL to https://jarbird.com/api/v1 and supply your Jarbird key.
Can I keep my OpenRouter model ID?
Yes, for models in the Jarbird catalogue. Verify streaming, tools, and other optional parameters with your own requests before switching production traffic.